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

    Neuronpedia

    INDEX
    Explanations

    website links, usernames, and hashtags

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     adm
    -0.73
     GOODMAN
    -0.68
     Aval
    -0.66
    IGHTS
    -0.65
     Lauder
    -0.63
     roy
    -0.63
     Catalyst
    -0.62
     thirds
    -0.62
    ģĸ
    -0.61
     EntityItem
    -0.60
    POSITIVE LOGITS
    odcast
    1.30
    aired
    1.23
    ivot
    1.19
    ossible
    1.19
    ulse
    1.17
    osit
    1.16
    redict
    1.16
    ublic
    1.12
    regnancy
    1.10
    ilot
    1.09
    Act Density 4.000%

    No Known Activations