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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     p
    -0.15
     Mart
    -0.14
    _MA
    -0.14
    ast
    -0.13
    à¸Ķย
    -0.13
     depr
    -0.13
    sey
    -0.13
    Mon
    -0.13
     pl
    -0.13
    ats
    -0.13
    POSITIVE LOGITS
    ucker
    0.16
    vu
    0.15
    beck
    0.15
     Trick
    0.15
    criptor
    0.14
    ubat
    0.14
    ç´
    0.14
    lessly
    0.14
    tür
    0.14
    大åħ¨
    0.14
    Act Density 0.137%

    No Known Activations