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

    Neuronpedia

    INDEX
    Explanations

    brackets and symbols indicating context or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Formatter
    -0.16
    lor
    -0.16
    rum
    -0.15
    gom
    -0.15
    ohen
    -0.15
    apan
    -0.15
    ignon
    -0.15
    lt
    -0.15
    leur
    -0.15
    ÑģÑĮ
    -0.14
    POSITIVE LOGITS
    296
    0.16
    chnitt
    0.15
    577
    0.15
    OrDefault
    0.15
    å±
    0.14
    665
    0.14
    265
    0.14
    inÄĽ
    0.14
    ichern
    0.14
    289
    0.14
    Act Density 0.012%

    No Known Activations