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

    Neuronpedia

    INDEX
    Explanations

    the word "in" with varying intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inqu
    -0.15
    -front
    -0.14
     Field
    -0.14
    Go
    -0.14
    Overlap
    -0.14
    vrier
    -0.13
    inp
    -0.13
    inand
    -0.13
     circum
    -0.13
     náv
    -0.13
    POSITIVE LOGITS
    rette
    0.17
    Luck
    0.16
    ocab
    0.15
    çe
    0.15
    annon
    0.15
    uden
    0.14
    دد
    0.14
    adoo
    0.14
    arence
    0.14
    ude
    0.14
    Act Density 0.014%

    No Known Activations