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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical logic and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vatar
    -0.71
     الحره
    -0.67
    }{*}{
    -0.67
    }{*}{}
    -0.57
    lielmo
    -0.57
    ciaż
    -0.56
    }$​
    -0.56
    ussis
    -0.56
    ▪️
    -0.55
    nasse
    -0.54
    POSITIVE LOGITS
     avoient
    0.96
     auffi
    0.95
     Reſ
    0.90
     étoient
    0.90
     Monfieur
    0.90
     purpoſe
    0.87
     figliu
    0.87
     ſta
    0.84
     pleaſure
    0.84
     gethan
    0.83
    Act Density 0.876%

    No Known Activations