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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of how something looks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe appearance or visual qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.69
    isSpecialOrderable
    -0.68
    ipl
    -0.64
    emetery
    -0.63
    ctrl
    -0.62
    trl
    -0.60
    Quotes
    -0.60
    MQ
    -0.59
    poons
    -0.59
     Newsp
    -0.58
    POSITIVE LOGITS
     like
    1.10
     nicer
    1.08
     alike
    1.02
     strikingly
    1.01
     awfully
    1.01
     identical
    0.99
     suspic
    0.93
     fantastic
    0.93
     remarkably
    0.92
     suspicious
    0.92
    Act Density 0.056%

    No Known Activations