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

    Neuronpedia

    INDEX
    Explanations

    words related to military or aggressive actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.67
     eminent
    -0.66
    liest
    -0.66
     cond
    -0.65
     cul
    -0.64
     privately
    -0.61
     timeless
    -0.60
     interven
    -0.60
     wa
    -0.59
    AUD
    -0.59
    POSITIVE LOGITS
    akery
    0.84
    ooter
    0.84
    oks
    0.84
    aders
    0.83
    ooters
    0.82
    olid
    0.82
    oche
    0.80
    izard
    0.79
    angs
    0.77
    ords
    0.76
    Act Density 0.101%

    No Known Activations