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

    Neuronpedia

    INDEX
    Explanations

    references to formal communications or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    659
    -0.19
    γά
    -0.18
    ëłµ
    -0.16
    cri
    -0.15
    eko
    -0.15
    yen
    -0.14
     ought
    -0.13
    aid
    -0.13
    åľ
    -0.13
    åıĹ
    -0.13
    POSITIVE LOGITS
     saying
    0.28
     about
    0.24
     pur
    0.23
     stating
    0.20
     regarding
    0.19
     asking
    0.18
     addressed
    0.18
     entitled
    0.18
     concerning
    0.17
     indicating
    0.16
    Act Density 0.241%

    No Known Activations