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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to admissions processes and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kl
    -0.16
    idor
    -0.16
    essim
    -0.16
    ington
    -0.15
     nhau
    -0.15
     Alt
    -0.15
    OF
    -0.15
    ann
    -0.14
    alt
    -0.14
    inen
    -0.14
    POSITIVE LOGITS
     vÃło
    0.20
     into
    0.19
    Into
    0.18
    ìĪł
    0.17
    _into
    0.17
    wap
    0.16
     Into
    0.16
     onto
    0.16
    into
    0.15
    erce
    0.15
    Act Density 0.030%

    No Known Activations