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

    Neuronpedia

    INDEX
    Explanations

    instances of positive sentiment or affirmation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     متعلقه
    -1.25
     purpoſe
    -1.17
    BeginContext
    -1.16
     autorytatywna
    -1.16
     Efq
    -1.08
     photolibrary
    -1.07
     Monfieur
    -1.07
    addCriterion
    -1.05
     raiſ
    -1.04
    InjectAttribute
    -1.03
    POSITIVE LOGITS
    pos
    1.42
     pos
    1.27
     Pos
    1.22
    Pos
    1.18
     POS
    1.07
    POS
    1.03
    Compos
    0.72
    ut
    0.69
    setPos
    0.68
     POST
    0.67
    Act Density 0.008%

    No Known Activations