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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating pauses or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chio
    -0.15
    imu
    -0.14
    atches
    -0.13
    æ´¥
    -0.13
     except
    -0.13
     aunque
    -0.13
     though
    -0.13
    atch
    -0.13
     forget
    -0.13
    bmp
    -0.13
    POSITIVE LOGITS
    while
    0.22
     whilst
    0.21
     while
    0.20
     WHILE
    0.20
    including
    0.19
    particularly
    0.19
     particularly
    0.18
     including
    0.18
    whether
    0.17
    å°¤
    0.17
    Act Density 0.316%

    No Known Activations