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

    Neuronpedia

    INDEX
    Explanations

    references to suicide or suicide bombers

    oai_token-act-pair · gpt-3.5-turbo

    references to suicide and related actions or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artisan
    -0.81
    heny
    -0.78
    asonic
    -0.76
    onde
    -0.70
    Avg
    -0.69
    ateur
    -0.67
    nis
    -0.67
     Collider
    -0.66
    uncture
    -0.65
    İ
    -0.64
    POSITIVE LOGITS
     suicide
    1.03
     bomber
    1.02
     bombers
    0.98
    icide
    0.98
    itated
    0.96
    itating
    0.94
    icides
    0.92
    zai
    0.89
     ide
    0.88
     prevention
    0.83
    Act Density 0.033%

    No Known Activations