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

    Neuronpedia

    INDEX
    Explanations

    mentions of high quantity or quality

    oai_token-act-pair · gpt-3.5-turbo

    references to high levels or qualities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.75
     Barg
    -0.73
    Advertisements
    -0.68
     Dare
    -0.66
     Canad
    -0.66
     Doct
    -0.65
     Gou
    -0.65
    âĹ¼
    -0.63
     Funny
    -0.63
    ignty
    -0.63
    POSITIVE LOGITS
     enough
    0.93
    enough
    0.84
     levels
    0.84
    lighting
    0.81
    school
    0.79
     bidder
    0.77
    ened
    0.77
     ceilings
    0.77
     level
    0.76
     altitude
    0.76
    Act Density 0.048%

    No Known Activations