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

    Neuronpedia

    INDEX
    Explanations

    mentions of study participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.49
     new
    -0.44
    ew
    -0.44
    os
    -0.43
     sprzedaży
    -0.42
    AxisAlignment
    -0.41
     Мексичка
    -0.40
     Kills
    -0.39
     law
    -0.39
     penjualan
    -0.38
    POSITIVE LOGITS
     participant
    1.23
     Participant
    1.22
    Participant
    1.16
    participant
    1.15
     Participants
    0.99
     participants
    0.96
    Participants
    0.93
    participants
    0.84
     participante
    0.72
     contestant
    0.71
    Act Density 0.008%

    No Known Activations