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

    Neuronpedia

    INDEX
    Explanations

    references to violence, particularly in relation to media and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endon
    -0.17
    esar
    -0.16
    iram
    -0.16
    elling
    -0.15
    ixels
    -0.15
    orias
    -0.15
    iron
    -0.14
    iven
    -0.14
    ied
    -0.14
    rollo
    -0.14
    POSITIVE LOGITS
    ence
    0.24
    ent
    0.22
    ENCE
    0.21
    ently
    0.19
     Consort
    0.18
    aceous
    0.18
    ations
    0.17
    ative
    0.17
    acea
    0.17
    ins
    0.17
    Act Density 0.004%

    No Known Activations