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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zew
    -0.17
    wit
    -0.15
    že
    -0.14
    agos
    -0.14
    ÑĮÑı
    -0.13
    ember
    -0.13
    림
    -0.13
    anke
    -0.13
    unders
    -0.13
    edy
    -0.13
    POSITIVE LOGITS
    usat
    0.17
    ksen
    0.15
    transition
    0.14
    _mgmt
    0.14
    è¯Ŀ
    0.14
    igue
    0.14
    kovi
    0.13
    ght
    0.13
    лиж
    0.13
    ackers
    0.13
    Act Density 0.154%

    No Known Activations