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

    Neuronpedia

    INDEX
    Explanations

    references to suicide

    oai_token-act-pair · gpt-3.5-turbo

    references to suicide and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heny
    -0.80
    asonic
    -0.76
    Avg
    -0.75
     Collider
    -0.72
    artisan
    -0.69
    Stud
    -0.68
     Phar
    -0.68
    rium
    -0.67
    aunder
    -0.66
    uncture
    -0.66
    POSITIVE LOGITS
     suicide
    1.12
     bomber
    1.11
    zai
    1.03
     bombers
    1.01
    itated
    0.99
    itating
    0.97
    icide
    0.95
     pact
    0.87
    icides
    0.86
     ide
    0.86
    Act Density 0.025%

    No Known Activations