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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing contrasts or comparisons between two or more items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rose
    -0.20
    shed
    -0.15
    igram
    -0.15
    ìĦ±ìĿĦ
    -0.15
    .Dispatch
    -0.15
    lio
    -0.15
     Gesture
    -0.14
    /read
    -0.14
    agma
    -0.14
    dur
    -0.14
    POSITIVE LOGITS
    iating
    0.21
    iator
    0.21
    /error
    0.20
     between
    0.20
    iale
    0.18
    iable
    0.18
    iative
    0.18
    ially
    0.16
    /div
    0.16
    icult
    0.16
    Act Density 0.039%

    No Known Activations