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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases indicating plans, schedules, or future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    दर
    -0.16
    indsight
    -0.15
    dea
    -0.15
    æijĺ
    -0.15
     Peak
    -0.14
    oup
    -0.14
    abyrin
    -0.14
     Karel
    -0.14
    ceae
    -0.14
    onya
    -0.14
    POSITIVE LOGITS
    .ret
    0.15
    APPER
    0.15
    ulen
    0.15
    KeyType
    0.14
    ivable
    0.14
    'gc
    0.14
    /request
    0.14
    CVE
    0.13
    edo
    0.13
    chu
    0.13
    Act Density 0.043%

    No Known Activations