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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns indicating self-reference

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     shit
    -0.60
    wapV
    -0.54
    Sheep
    -0.53
    mitian
    -0.52
     sense
    -0.51
     tư
    -0.51
    нят
    -0.51
    EqualsAnd
    -0.51
    isUser
    -0.51
     Quicks
    -0.51
    POSITIVE LOGITS
    WireFormatLite
    0.72
     snippetHide
    0.71
    RectangleBorder
    0.66
     onBind
    0.64
    findpost
    0.63
    ValueStyle
    0.62
     صوتيه
    0.59
    InjectAttribute
    0.58
    
    0.57
     للمعارف
    0.57
    Act Density 0.013%

    No Known Activations