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

    Neuronpedia

    INDEX
    Explanations

    themes related to societal issues and personal experiences with change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    िलत
    -0.18
    ibold
    -0.14
    ãģªãģ®
    -0.14
     olab
    -0.14
    ’ve
    -0.14
     Was
    -0.14
    Å¡ov
    -0.14
    Was
    -0.14
    ennent
    -0.13
     sometimes
    -0.13
    POSITIVE LOGITS
     will
    1.18
    will
    1.00
     sẽ
    0.84
    ä¼ļ
    0.80
     akan
    0.78
    æľĥ
    0.78
    'll
    0.76
    ’ll
    0.75
     WILL
    0.74
    Will
    0.73
    Act Density 2.355%

    No Known Activations