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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and their surrounding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alytics
    -0.16
    (which
    -0.16
    оÑģÑĤаÑĤ
    -0.14
    ...\
    -0.14
    whose
    -0.14
     whose
    -0.14
    resizing
    -0.14
    oad
    -0.14
     èĩªåĬ¨çĶŁæĪIJ
    -0.14
    nam
    -0.13
    POSITIVE LOGITS
     but
    0.27
     yet
    0.26
     border
    0.19
     even
    0.19
     and
    0.17
     like
    0.17
    Yet
    0.17
     Yet
    0.16
    even
    0.16
     because
    0.16
    Act Density 0.137%

    No Known Activations