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

    Neuronpedia

    INDEX
    Explanations

    terms related to suicide and self-harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    suicide and suicidal thoughts

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of suicide, self-harm, or suicidal actions/intent (including attempts and hanging).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.44
     gus
    -0.41
     hob
    -0.39
    ứng
    -0.38
    iNdEx
    -0.38
    zins
    -0.38
    Personendaten
    -0.37
    hoho
    -0.37
    sApp
    -0.37
     Spell
    -0.37
    POSITIVE LOGITS
     suicide
    1.13
    suicide
    0.96
     suicidio
    0.95
    Suicide
    0.94
     suicides
    0.88
     suicidal
    0.85
     Suicide
    0.84
    自杀
    0.77
    自殺
    0.73
     suic
    0.71
    Act Density 0.174%

    No Known Activations