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

    Neuronpedia

    INDEX
    Explanations

    terms related to suicide attempts and self-harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.74
     Paglinawan
    -0.64
     Roskov
    -0.64
    RegressionTest
    -0.63
    ']")
    -0.59
    Autoritní
    -0.59
    :✨
    -0.57
    addCriterion
    -0.56
    IContainer
    -0.55
    новниш
    -0.54
    POSITIVE LOGITS
     suicide
    1.82
     commit
    1.59
     Suicide
    1.57
    suicide
    1.47
     suicides
    1.44
     suicidal
    1.43
    Suicide
    1.42
     committed
    1.41
     committing
    1.40
     Commit
    1.39
    Act Density 0.237%

    No Known Activations