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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ali
    -0.17
    sein
    -0.17
    orent
    -0.15
    ält
    -0.15
    retty
    -0.15
     boring
    -0.14
    allo
    -0.14
    ALI
    -0.14
    inar
    -0.14
    lope
    -0.13
    POSITIVE LOGITS
     whether
    0.17
    ForObject
    0.16
    elog
    0.15
     Whether
    0.15
    ваÑĤ
    0.14
    ebi
    0.14
    .gridColumn
    0.14
    whether
    0.14
    :.:
    0.14
     exactly
    0.14
    Act Density 0.042%

    No Known Activations