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

    Neuronpedia

    INDEX
    Explanations

    mentions of injuries and physical harm

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries and fatalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     virtue
    -0.76
     virtues
    -0.73
    channelAvailability
    -0.70
     Teach
    -0.69
     monog
    -0.68
     veto
    -0.68
    æ©Ł
    -0.66
     monopol
    -0.66
     Britann
    -0.66
     royalties
    -0.66
    POSITIVE LOGITS
    lass
    0.86
    nsic
    0.85
    EMS
    0.85
    د
    0.83
    bris
    0.83
    nsics
    0.82
     charred
    0.82
    abre
    0.79
     debris
    0.78
     recovered
    0.75
    Act Density 0.288%

    No Known Activations