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

    Neuronpedia

    INDEX
    Explanations

    mentions of injury and the consequences of harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.15
    lasses
    -0.15
    uely
    -0.14
    .Îł
    -0.14
    iasi
    -0.14
    sect
    -0.13
    kir
    -0.13
    aura
    -0.13
    rgan
    -0.13
    irit
    -0.13
    POSITIVE LOGITS
    acco
    0.16
     Bil
    0.13
    )const
    0.13
    她们
    0.13
    asher
    0.13
    CAPE
    0.12
    KNOWN
    0.12
    Streamer
    0.12
    CEE
    0.12
    .scalar
    0.12
    Act Density 0.106%

    No Known Activations