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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or conditional phrasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -0.81
    Datuak
    -0.80
     pleaſure
    -0.78
    ſelf
    -0.72
     myſelf
    -0.71
     Houſe
    -0.69
     Jefus
    -0.69
     épreuve
    -0.69
     houſe
    -0.69
     itſelf
    -0.68
    POSITIVE LOGITS
    anskje
    1.29
    Maybe
    1.23
     Maybe
    1.19
    maybe
    1.19
     maybe
    1.15
     perhaps
    1.02
     Perhaps
    1.02
    Perhaps
    1.00
    perhaps
    0.99
     quizás
    0.89
    Act Density 0.057%

    No Known Activations