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

    Neuronpedia

    INDEX
    Explanations

    game mechanics and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickey
    -0.17
    assa
    -0.16
    vard
    -0.15
    ثر
    -0.15
    Æ¡i
    -0.15
    asy
    -0.15
     вел
    -0.14
    ä¸į足
    -0.14
    avan
    -0.14
    offset
    -0.14
    POSITIVE LOGITS
    kaar
    0.16
    iev
    0.15
     objective
    0.15
     goal
    0.14
    åŃ
    0.14
    indre
    0.14
    éħį
    0.14
    .pp
    0.14
    è¨
    0.14
     Revel
    0.14
    Act Density 0.083%

    No Known Activations