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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its variations, indicating direction or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strcasecmp
    -0.15
    aná
    -0.15
    )prepare
    -0.15
    taire
    -0.15
     सब
    -0.14
     поба
    -0.14
    Ø·ÙĨ
    -0.14
    辺
    -0.14
    ogne
    -0.14
    awks
    -0.14
    POSITIVE LOGITS
    mada
    0.17
    gateway
    0.15
    elong
    0.14
    qi
    0.14
    è¾°
    0.14
    at
    0.14
    ìĸij
    0.14
    Mapped
    0.14
    mc
    0.14
     flashed
    0.14
    Act Density 0.043%

    No Known Activations