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

    Neuronpedia

    INDEX
    Explanations

    specific non-English or specialized characters and scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    men
    -0.56
     fast
    -0.55
    g
    -0.54
     my
    -0.54
    ges
    -0.54
    -0.53
    ff
    -0.53
     one
    -0.53
    iste
    -0.52
    ans
    -0.52
    POSITIVE LOGITS
     itſelf
    1.01
     étoit
    0.93
     feroit
    0.90
     avoient
    0.88
     ainfi
    0.88
     autorytatywna
    0.86
     Majefty
    0.85
     pleaſure
    0.84
     Anſ
    0.83
     moſt
    0.83
    Act Density 0.208%
    No Known Activations