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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    instances of statements that assert or affirm a conclusion or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.74
    ieval
    -0.70
    igs
    -0.69
    arted
    -0.68
    dden
    -0.67
    BuyableInstoreAndOnline
    -0.66
     FG
    -0.63
    si
    -0.63
    imental
    -0.60
    xia
    -0.59
    POSITIVE LOGITS
     cru
    0.80
     downright
    0.75
     damned
    0.73
     horm
    0.73
     damn
    0.72
     therein
    0.72
     predictably
    0.71
     darn
    0.69
     certainly
    0.69
     Solitaire
    0.68
    Act Density 0.503%

    No Known Activations