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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iegel
    -0.16
    alian
    -0.15
    åĤ
    -0.15
    TagName
    -0.14
    131
    -0.14
    esser
    -0.14
    reetings
    -0.13
    acky
    -0.13
    u
    -0.13
     lax
    -0.13
    POSITIVE LOGITS
    ainer
    0.18
    azon
    0.18
    lev
    0.16
    atrix
    0.16
     OTHERWISE
    0.15
    egal
    0.15
    arget
    0.15
    phan
    0.15
     BATCH
    0.14
    rames
    0.14
    Act Density 0.004%

    No Known Activations