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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating alternative options or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.58
     Marconi
    -0.56
     himſelf
    -0.56
     myſelf
    -0.56
    Спасибо
    -0.55
     subclasses
    -0.55
    JvmStatic
    -0.54
    참고
    -0.54
     Fontana
    -0.54
    日閲覧
    -0.53
    POSITIVE LOGITS
     للمعارف
    0.60
     calendriers
    0.60
     AssemblyTitle
    0.60
    ExtendWith
    0.53
    concel
    0.52
    ValueStyle
    0.51
     одни
    0.51
    gonic
    0.50
    เล
    0.50
     Од
    0.49
    Act Density 0.371%

    No Known Activations