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

    Neuronpedia

    INDEX
    Explanations

    numerical values and symbols associated with ratings or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.17
     itſelf
    -1.08
     Monfieur
    -1.06
     Theſe
    -1.02
     raiſ
    -1.00
     purpoſe
    -0.97
     Jefus
    -0.96
    ſelf
    -0.96
     whoſe
    -0.93
     ainfi
    -0.93
    POSITIVE LOGITS
    classnames
    0.88
    vė
    0.58
     autorytatywna
    0.55
    toggleClass
    0.52
    arbon
    0.51
     makeStyles
    0.51
    ונות
    0.48
    ↵↵
    0.47
    classNames
    0.46
     n
    0.45
    Act Density 0.417%

    No Known Activations