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

    Neuronpedia

    INDEX
    Explanations

    things related to threats and danger

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricks
    -0.85
    urses
    -0.81
    arist
    -0.76
     Band
    -0.70
    gian
    -0.67
    iband
    -0.67
    tein
    -0.67
    cise
    -0.66
    mys
    -0.65
    baum
    -0.65
    POSITIVE LOGITS
     posed
    1.23
     threat
    0.89
     threats
    0.81
     emanating
    0.80
    crow
    0.78
     glare
    0.74
    threat
    0.74
     deterrent
    0.72
    xual
    0.71
    lessly
    0.70
    Act Density 0.057%

    No Known Activations