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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "literally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĮ
    -0.17
    vida
    -0.15
    atz
    -0.15
    à¸į
    -0.14
     Hayward
    -0.14
    icl
    -0.14
    ÑĢави
    -0.14
    vä
    -0.14
    uppy
    -0.14
    eprom
    -0.14
    POSITIVE LOGITS
    uset
    0.15
    lica
    0.15
    um
    0.15
    fy
    0.15
    578
    0.14
    ITERAL
    0.14
    erator
    0.14
    mente
    0.14
    ums
    0.14
    raud
    0.14
    Act Density 0.009%

    No Known Activations