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

    Neuronpedia

    INDEX
    Explanations

    references to suicide and mental health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UGIN
    -0.17
    ucch
    -0.15
    .yahoo
    -0.15
    riba
    -0.15
    -mf
    -0.15
    illis
    -0.14
    illage
    -0.14
    GMT
    -0.14
    virtual
    -0.14
    íĮĮ
    -0.14
    POSITIVE LOGITS
     suicide
    0.41
     Suicide
    0.39
     suicidal
    0.36
     suicides
    0.35
     suic
    0.33
    Su
    0.30
     Su
    0.29
    su
    0.28
    _su
    0.24
     SU
    0.23
    Act Density 0.108%

    No Known Activations