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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.83
    ftagPool
    -0.77
    StructEnd
    -0.77
    tagHelperRunner
    -0.76
     betweenstory
    -0.75
    ConstraintMaker
    -0.74
     الدولى
    -0.69
     ModelExpression
    -0.68
    IntoConstraints
    -0.67
    istoitu
    -0.66
    POSITIVE LOGITS
    vestream
    0.51
     shouldn
    0.45
     Höchst
    0.45
    pecha
    0.45
     vô
    0.44
    cesso
    0.44
     isn
    0.44
    ribut
    0.43
    cinogen
    0.43
     great
    0.42
    Act Density 0.389%

    No Known Activations