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

    Neuronpedia

    INDEX
    Explanations

    words that indicate actions, especially in the context of engagement or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucken
    -0.17
    ÏĢοÏħ
    -0.17
    pread
    -0.16
    licken
    -0.15
    ADOR
    -0.15
    striction
    -0.14
     restart
    -0.14
     coloring
    -0.14
     Slate
    -0.14
    ÏĨα
    -0.14
    POSITIVE LOGITS
    İ
    0.15
    رÛĮاÙĨ
    0.15
    asio
    0.15
    wi
    0.14
    lette
    0.14
    cher
    0.14
    atchet
    0.14
    isoft
    0.13
    raries
    0.13
    itos
    0.13
    Act Density 0.206%

    No Known Activations