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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being widely acknowledged, widely distributed, and widely seen

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating widespread acceptance or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cair
    -0.79
     Odyssey
    -0.72
    agate
    -0.71
    ourke
    -0.69
    hetics
    -0.67
    ngth
    -0.67
     Gemini
    -0.66
    iry
    -0.63
    thur
    -0.63
    alus
    -0.63
    POSITIVE LOGITS
     regarded
    1.20
     dispersed
    1.04
     spaced
    1.02
     accepted
    1.00
     viewed
    1.00
     distributed
    0.99
     publicized
    0.98
     acclaimed
    0.95
     circulated
    0.95
     considered
    0.92
    Act Density 0.035%

    No Known Activations