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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "positive" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.16
    aza
    -0.16
    aso
    -0.16
    asley
    -0.15
    ateur
    -0.15
    YST
    -0.14
    íĥĿ
    -0.14
    leÅŁ
    -0.14
    yles
    -0.14
    ulia
    -0.14
    POSITIVE LOGITS
    ITIVE
    0.20
    gresql
    0.19
    greSQL
    0.19
    assium
    0.18
    sum
    0.18
    =pos
    0.17
    ibilities
    0.17
    adlo
    0.17
    itivity
    0.17
    /n
    0.17
    Act Density 0.021%

    No Known Activations