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

    Neuronpedia

    INDEX
    Explanations

    locations, names, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas in relation to lists or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lust
    -0.66
    ocial
    -0.66
    worldly
    -0.66
    Ľ
    -0.65
    olly
    -0.65
    sid
    -0.65
    zbek
    -0.63
    hra
    -0.63
    ommel
    -0.63
    omething
    -0.62
    POSITIVE LOGITS
     etc
    1.03
    76561
    1.00
     Lanc
    0.71
     Phi
    0.67
     Scorp
    0.65
     Britann
    0.64
     Born
    0.63
     Kinnikuman
    0.63
     Calif
    0.62
     Boll
    0.61
    Act Density 0.314%

    No Known Activations