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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izzato
    -0.16
    ensa
    -0.15
    _fault
    -0.15
     Shake
    -0.14
    estro
    -0.13
    коÑĤ
    -0.13
    <Props
    -0.13
    319
    -0.13
    auc
    -0.13
    INS
    -0.13
    POSITIVE LOGITS
     prevent
    0.32
     avoid
    0.32
     morb
    0.27
     mor
    0.24
     Mor
    0.22
    avoid
    0.21
     unt
    0.21
     deaths
    0.20
     costly
    0.20
     DAL
    0.20
    Act Density 0.136%

    No Known Activations