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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emphasizing a point or providing context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of awareness and consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.78
    urated
    -0.63
     )]
    -0.63
    ãĤ¤
    -0.60
    nect
    -0.60
    ãĥŀ
    -0.59
    Ãį
    -0.59
    Said
    -0.57
    attering
    -0.57
    <?
    -0.56
    POSITIVE LOGITS
     that
    1.14
     though
    0.94
     however
    0.90
     THAT
    0.84
     here
    0.83
    that
    0.83
     lest
    0.80
     how
    0.69
    adays
    0.68
     there
    0.68
    Act Density 0.138%

    No Known Activations