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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric or date-related formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (HTTP
    -0.15
     HD
    -0.14
     day
    -0.14
     Beck
    -0.14
    497
    -0.14
    omi
    -0.14
    ers
    -0.14
     Day
    -0.13
     Dual
    -0.13
    ế
    -0.13
    POSITIVE LOGITS
     Kosovo
    0.15
    ZERO
    0.15
    大åħ¨
    0.15
    ziel
    0.14
    çĪ½
    0.14
    _tip
    0.14
    kos
    0.14
    ëŀ«
    0.14
    ť
    0.13
    Æ°Æ¡ng
    0.13
    Act Density 0.001%

    No Known Activations