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

    Neuronpedia

    INDEX
    Explanations

    contractions and certain informal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æľĭ
    -0.17
    ereal
    -0.15
    encil
    -0.14
    gars
    -0.14
    inho
    -0.14
    utsch
    -0.14
    869
    -0.13
    á»įng
    -0.13
    à¸į
    -0.13
    mah
    -0.13
    POSITIVE LOGITS
     said
    0.20
     Said
    0.17
     stuff
    0.16
    /misc
    0.16
     somebody
    0.16
     miscellaneous
    0.16
    said
    0.15
     oneself
    0.15
    wor
    0.15
     misc
    0.14
    Act Density 0.000%

    No Known Activations