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

    Neuronpedia

    INDEX
    Explanations

    sentences that emphasize personal experiences and self-reflection

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

    I/she + verb describing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.93
    AddTagHelper
    -0.83
    MigrationBuilder
    -0.71
    Hentet
    -0.71
    LookAnd
    -0.71
    GIVEREF
    -0.71
    DockStyle
    -0.67
     ujednoznacz
    -0.67
     snippetHide
    -0.66
    ########.
    -0.66
    POSITIVE LOGITS
    The
    0.50
     The
    0.39
    There
    0.36
     are
    0.35
     consigo
    0.34
    しくて
    0.31
     There
    0.31
    De
    0.30
    SC
    0.30
    の中には
    0.30
    Act Density 0.066%

    No Known Activations