Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to self-reflection and self-assessment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hyphenated compounds prefixed with “self-,” strongly activating on the hyphen and the ensuing term.

    oai_token-act-pair · gpt-5Triggered by @timna

    self

    np_max-act-logits · deepseek-r1Triggered by @arielgoldsteinlab

    The token "self" used as a prefix forming compound nouns related to autonomous actions or states (e.g., monitoring, assessment, regulation).

    eleuther_acts_top20 · deepseek-r1Triggered by @arielgoldsteinlab

    self

    np_max-act · gpt-5Triggered by @arielgoldsteinlab

    self

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab

    hyphenated compound words starting with "self-".

    oai_token-act-pair · deepseek-r1Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    OGND
    -1.21
     snippetHide
    -1.02
    DockStyle
    -0.92
    ✨:
    -0.89
     дописавши
    -0.89
     utafitiHapana
    -0.83
    richTextPanel
    -0.81
    AnchorStyles
    -0.81
    StreetMap
    -0.80
     typelib
    -0.80
    POSITIVE LOGITS
     SELF
    1.54
     Self
    1.46
     self
    1.45
    SELF
    1.39
    Self
    1.36
    self
    1.27
     selves
    0.99
    ELF
    0.90
    elf
    0.90
    selves
    0.82
    Act Density 0.066%

    No Known Activations