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

    Neuronpedia

    INDEX
    Explanations

    occurrences of non-informative content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ban
    -0.65
     scha
    -0.65
    -
    -0.63
     Te
    -0.61
     bu
    -0.58
     points
    -0.55
    ,
    -0.54
     te
    -0.54
     ver
    -0.54
     ad
    -0.54
    POSITIVE LOGITS
     Jefus
    1.31
     myſelf
    1.28
     itſelf
    1.25
     Anſ
    1.25
     Houſe
    1.21
     auffi
    1.19
     himſelf
    1.18
     pleaſure
    1.15
    ſelf
    1.14
     ſeveral
    1.14
    Act Density 0.257%

    No Known Activations