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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the substring 'com'

    oai_token-act-pair · gpt-3.5-turbo

    words related to community or companionship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kubrick
    -0.80
    DragonMagazine
    -0.68
     Icelandic
    -0.67
     Sinclair
    -0.62
     rink
    -0.62
    YL
    -0.60
     Isles
    -0.59
     Rebels
    -0.59
     Jackets
    -0.59
     Siem
    -0.59
    POSITIVE LOGITS
    forts
    1.09
    ptroller
    1.08
    pleting
    1.03
    mented
    0.97
    ittee
    0.96
    rade
    0.94
    legate
    0.91
    etary
    0.91
    sat
    0.90
    meric
    0.90
    Act Density 0.010%

    No Known Activations