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

    Neuronpedia

    INDEX
    Explanations

    instances of the words "end" and "ended."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    away
    -0.16
    331
    -0.16
    chester
    -0.15
    laus
    -0.15
    atak
    -0.15
    mo
    -0.14
    ÙĨدÙĩ
    -0.14
    çi
    -0.14
    OX
    -0.14
    forme
    -0.14
    POSITIVE LOGITS
     up
    0.36
    -up
    0.26
    .up
    0.18
     ended
    0.18
    ow
    0.17
    ëĵĿ
    0.17
    up
    0.17
    elman
    0.17
    orses
    0.17
    -Up
    0.17
    Act Density 0.014%

    No Known Activations