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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons on a scale or in relation to something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to relationships or comparisons involving the term "relative."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eret
    -0.96
    emi
    -0.85
    session
    -0.74
    iak
    -0.73
    tub
    -0.73
     Tatt
    -0.71
    jet
    -0.69
     Springs
    -0.68
    oval
    -0.67
    printed
    -0.67
    POSITIVE LOGITS
     humidity
    1.22
     obscurity
    1.14
     inexper
    1.13
     importance
    1.13
     scarcity
    1.11
     newcomer
    1.11
     merits
    1.01
     anonymity
    1.00
     abundance
    0.97
     ease
    0.96
    Act Density 0.043%

    No Known Activations