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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing frustration or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Informal language or playful mockery

    np_acts-logits-general · gemini-2.0-flash

    messing around with nonsense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.83
    endforeach
    -0.58
    cèse
    -0.57
    </thead>
    -0.56
     aapt
    -0.56
    dataProvider
    -0.54
     ciudadana
    -0.51
     tịch
    -0.51
     pire
    -0.50
     跳转至
    -0.50
    POSITIVE LOGITS
     fancy
    0.74
     nahilalakip
    0.70
     nonsense
    0.70
     messing
    0.63
     shenanigans
    0.62
     gim
    0.61
     tricks
    0.60
     ErrIntOverflow
    0.58
     gimmick
    0.58
     coy
    0.57
    Act Density 0.209%

    No Known Activations