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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to obligations or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     veiks
    -0.65
    hdashline
    -0.63
     Egipto
    -0.62
    UnitTesting
    -0.60
    didSet
    -0.56
    Pill
    -0.54
     diaphragm
    -0.53
    theon
    -0.51
     óptica
    -0.51
    oken
    -0.50
    POSITIVE LOGITS
     must
    0.87
     ModelExpression
    0.82
    must
    0.78
     Must
    0.76
    Must
    0.75
    SharedDtor
    0.73
     MUST
    0.69
    featureID
    0.68
    uxxxx
    0.66
    >");
    0.65
    Act Density 0.113%

    No Known Activations