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

    Neuronpedia

    INDEX
    Explanations

    words related to entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.17
    ãĥ£
    -0.17
    izon
    -0.16
    559
    -0.16
    eller
    -0.15
    essel
    -0.15
    thur
    -0.14
    è¡
    -0.14
    lett
    -0.14
    clair
    -0.14
    POSITIVE LOGITS
    nan
    0.18
    uhan
    0.15
    iyon
    0.15
    zin
    0.15
    TA
    0.15
    Æ°á»Ŀi
    0.15
    تا
    0.15
     pij
    0.15
    ta
    0.14
    ulace
    0.14
    Act Density 0.000%

    No Known Activations