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

    Neuronpedia

    INDEX
    Explanations

    references to victims of violent incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çļ
    -0.75
     externalToEVAOnly
    -0.72
    ivalry
    -0.72
    ãĥ¢
    -0.70
    é¾įå¥ij士
    -0.69
     Publication
    -0.67
    atism
    -0.67
    toggle
    -0.66
     guiActiveUnfocused
    -0.65
    roman
    -0.65
    POSITIVE LOGITS
     identified
    0.92
     traumat
    0.90
     identifiable
    0.88
     bystanders
    0.85
     juveniles
    0.85
     hospitalized
    0.84
     herself
    0.84
     raped
    0.81
     unborn
    0.79
     unidentified
    0.79
    Act Density 0.163%

    No Known Activations