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

    Neuronpedia

    INDEX
    Explanations

    incidents involving physical harm or violence

    oai_token-act-pair · gpt-3.5-turbo

    events involving violent actions or assaults

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.80
     singular
    -0.74
     extraord
    -0.70
     aster
    -0.69
     thous
    -0.68
     clich
    -0.67
     understatement
    -0.66
     miracle
    -0.66
     everlasting
    -0.65
     miracles
    -0.62
    POSITIVE LOGITS
     biking
    0.92
     bicy
    0.91
     travelling
    0.90
     attempting
    0.88
     protesting
    0.88
     fleeing
    0.87
     parked
    0.86
     hiking
    0.86
     filming
    0.83
     exercising
    0.83
    Act Density 0.294%

    No Known Activations