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

    Neuronpedia

    INDEX
    Explanations

    words of recommendation or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unkt
    -0.44
    нд
    -0.43
     Cout
    -0.43
    egrave
    -0.42
     und
    -0.42
    ACC
    -0.42
     dét
    -0.41
    ført
    -0.41
     albicans
    -0.41
    fib
    -0.41
    POSITIVE LOGITS
     ostavi
    0.84
     Efq
    0.84
     createState
    0.81
    TypedDataSet
    0.80
    LookAnd
    0.79
     ProtoMessage
    0.78
    contentLoaded
    0.78
     BoxFit
    0.77
    rizona
    0.74
    AntiForgeryToken
    0.72
    Act Density 0.055%

    No Known Activations