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

    Neuronpedia

    INDEX
    Explanations

    references to threats and dangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uinal
    -0.70
     scolas
    -0.66
     Swanson
    -0.66
    Absorption
    -0.65
    inyin
    -0.64
    unny
    -0.63
    urator
    -0.63
     AppCompat
    -0.62
    ודם
    -0.61
    TypedDataSet
    -0.61
    POSITIVE LOGITS
     threat
    1.80
    threat
    1.72
     Threat
    1.71
     threats
    1.69
    Threat
    1.62
     Threats
    1.62
    Threats
    1.39
     threatened
    1.39
     threatens
    1.37
     threatening
    1.33
    Act Density 0.065%

    No Known Activations