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

    Neuronpedia

    INDEX
    Explanations

    words related to disruption, agitation, or distress

    oai_token-act-pair · gpt-3.5-turbo

    words related to disturbance and unsettling experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.82
    gerald
    -0.75
    oled
    -0.73
    amacare
    -0.70
    ophers
    -0.70
    eah
    -0.69
    glas
    -0.69
    gil
    -0.68
    atar
    -0.67
    imb
    -0.66
    POSITIVE LOGITS
    ingly
    0.92
     disturb
    0.73
    urnal
    0.73
     awaken
    0.68
     Geo
    0.67
     disturbed
    0.66
    ktop
    0.63
    ĸļ
    0.63
     disturbances
    0.63
     distur
    0.63
    Act Density 0.028%

    No Known Activations