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

    Neuronpedia

    INDEX
    Explanations

    references to files and their versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urer
    -0.15
    monkey
    -0.14
    angan
    -0.14
    ango
    -0.14
    _REPORT
    -0.14
    lamak
    -0.14
    zeit
    -0.14
    rena
    -0.14
    klä
    -0.13
    reff
    -0.13
    POSITIVE LOGITS
    agoon
    0.17
    Äĥr
    0.15
    priv
    0.15
    MBED
    0.15
    bite
    0.15
    htag
    0.15
    orde
    0.15
    ucene
    0.15
    tile
    0.14
    enton
    0.14
    Act Density 0.028%

    No Known Activations