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

    Neuronpedia

    INDEX
    Explanations

    the word "speak" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omite
    -0.17
    rious
    -0.16
    TEGER
    -0.15
    licit
    -0.15
    iore
    -0.14
    urnished
    -0.14
    물
    -0.14
    cmc
    -0.14
    à¥Įर
    -0.14
     wide
    -0.14
    POSITIVE LOGITS
     '..',
    0.15
    BYTES
    0.15
    NoSuch
    0.14
    ewe
    0.14
    allen
    0.14
    erm
    0.14
    ENO
    0.14
    atures
    0.14
    XObject
    0.13
    arma
    0.13
    Act Density 0.016%

    No Known Activations