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

    Neuronpedia

    INDEX
    Explanations

    inquiries about opinions or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ightly
    -0.15
    weit
    -0.15
    oz
    -0.14
    á»ķ
    -0.13
    avan
    -0.13
     otherwise
    -0.13
    TOTYPE
    -0.13
     èı²å¾ĭ宾
    -0.13
    lobs
    -0.13
    ict
    -0.13
    POSITIVE LOGITS
     think
    0.56
     thinks
    0.50
     Think
    0.49
     thoughts
    0.47
    Think
    0.47
    think
    0.44
     thought
    0.42
     thinking
    0.42
     THINK
    0.41
     Thoughts
    0.40
    Act Density 0.043%

    No Known Activations