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

    Neuronpedia

    INDEX
    Explanations

    specific names or terms, potentially in a political or legal context

    oai_token-act-pair · gpt-3.5-turbo

    punctuation markers, especially colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uton
    -0.85
    lag
    -0.71
     bidder
    -0.68
    ivable
    -0.66
     rule
    -0.66
    etheless
    -0.65
     typ
    -0.64
    ibur
    -0.63
     sale
    -0.63
     brewing
    -0.61
    POSITIVE LOGITS
     WATCHED
    0.79
     COVER
    0.76
    FX
    0.73
    Channel
    0.72
     Gru
    0.71
    atform
    0.70
     Channel
    0.70
    HAEL
    0.69
     STORY
    0.69
     Spotlight
    0.68
    Act Density 0.065%

    No Known Activations