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

    Neuronpedia

    INDEX
    Explanations

    concepts related to suicide and depression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Krone
    -0.57
     Khanna
    -0.53
     BorderRadius
    -0.53
    wesenheit
    -0.51
    losseum
    -0.49
    恭喜
    -0.49
    ❋
    -0.47
    staw
    -0.47
     Lanes
    -0.46
    jestic
    -0.46
    POSITIVE LOGITS
     suicide
    1.65
    Suicide
    1.49
    suicide
    1.49
     Suicide
    1.43
     suicides
    1.27
     suic
    1.23
     suicidio
    1.17
     suicidal
    1.11
    自殺
    1.06
    自杀
    1.02
    Act Density 0.092%

    No Known Activations