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

    Neuronpedia

    INDEX
    Explanations

    tentative language indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.06
     himſelf
    -0.96
     myſelf
    -0.93
     itſelf
    -0.88
     Jefus
    -0.87
     houſe
    -0.84
     Houſe
    -0.83
     themſelves
    -0.81
    ſelf
    -0.80
    AndEndTag
    -0.80
    POSITIVE LOGITS
     perhaps
    1.47
    anskje
    1.43
     maybe
    1.43
    Maybe
    1.42
    perhaps
    1.41
     Perhaps
    1.41
    maybe
    1.40
     Maybe
    1.39
    Perhaps
    1.37
     quizás
    1.14
    Act Density 0.063%

    No Known Activations