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

    Neuronpedia

    INDEX
    Explanations

    instances of violence and injury related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mode
    -0.58
     Mode
    -0.54
    닙
    -0.53
     cref
    -0.53
    contextMenu
    -0.50
    iempos
    -0.49
    ündig
    -0.48
    ugier
    -0.48
    mism
    -0.47
    igshid
    -0.47
    POSITIVE LOGITS
     unconscious
    1.07
     lying
    0.95
     bleeding
    0.93
     Lying
    0.85
     slumped
    0.84
     inconsciente
    0.84
     fainted
    0.82
     conv
    0.82
     wri
    0.82
     limp
    0.82
    Act Density 0.309%

    No Known Activations