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

    Neuronpedia

    INDEX
    Explanations

    references to time frames and specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.75
    IndentedString
    -0.69
     BorderRadius
    -0.69
     فريبيس
    -0.66
    AntiForgeryToken
    -0.64
    хьтан
    -0.63
    MLLoader
    -0.63
    makeConstraints
    -0.63
    IntoConstraints
    -0.61
     Administrativna
    -0.59
    POSITIVE LOGITS
     late
    0.58
     September
    0.57
     December
    0.56
     Thursday
    0.55
    اریخ
    0.54
     February
    0.54
     July
    0.53
     early
    0.52
     November
    0.51
     June
    0.51
    Act Density 0.428%

    No Known Activations