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

    Neuronpedia

    INDEX
    Explanations

    references to highlighting, pointing out, or noting important information or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /full
    -0.15
    atures
    -0.14
    ampo
    -0.14
    inand
    -0.14
    osi
    -0.14
    ched
    -0.14
    .ObjectModel
    -0.13
    upp
    -0.13
    /if
    -0.13
    according
    -0.13
    POSITIVE LOGITS
     how
    0.27
     occasions
    0.23
    how
    0.20
     examples
    0.20
     ways
    0.20
     instances
    0.19
     several
    0.19
     repeatedly
    0.18
     Instances
    0.17
     ëªĩ
    0.17
    Act Density 0.074%

    No Known Activations