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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers related to events and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.57
     معه
    -0.54
    {}/
    -0.52
    EndInit
    -0.51
    omus
    -0.50
    setArguments
    -0.48
    asjonen
    -0.48
    builtin
    -0.48
    zysta
    -0.48
    enerys
    -0.46
    POSITIVE LOGITS
     afternoon
    0.95
     pukul
    0.91
     midnight
    0.89
     noon
    0.83
     الساعة
    0.81
     morning
    0.81
     evening
    0.80
    evening
    0.79
    midnight
    0.78
    afternoon
    0.77
    Act Density 0.335%

    No Known Activations