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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns and expressions of self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.66
    تیب
    -0.66
    ectady
    -0.63
    ici
    -0.58
     quæ
    -0.58
    عنی
    -0.58
    StoryboardSegue
    -0.57
    OGND
    -0.57
    er
    -0.57
    tabular
    -0.57
    POSITIVE LOGITS
    SELF
    0.77
    skraft
    0.68
    selves
    0.65
    RegressionTest
    0.64
    Referências
    0.60
    ändig
    0.58
    standig
    0.58
    ELF
    0.56
     naw
    0.55
    Heer
    0.54
    Act Density 0.057%

    No Known Activations