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

    Neuronpedia

    INDEX
    Explanations

    phrases related to threats, especially those related to security

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various types of threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    need
    -0.75
    ket
    -0.72
    aram
    -0.72
     Cosponsors
    -0.71
     Edited
    -0.70
    iard
    -0.70
    Reviewed
    -0.66
    NH
    -0.65
    rette
    -0.65
    tions
    -0.64
    POSITIVE LOGITS
     livelihood
    1.06
     morale
    0.91
     viability
    0.90
     sanity
    0.86
     civilization
    0.84
     survival
    0.83
     biodiversity
    0.82
     unborn
    0.81
     civilisation
    0.81
     humankind
    0.80
    Act Density 0.114%

    No Known Activations