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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ApplicationException
    -0.16
    stick
    -0.15
    ablo
    -0.14
    agua
    -0.14
     Mond
    -0.13
    es
    -0.13
    elsen
    -0.13
    lue
    -0.13
    platz
    -0.13
    uu
    -0.13
    POSITIVE LOGITS
    ahkan
    0.16
    NCY
    0.15
     Ass
    0.14
    OKIE
    0.14
    è½½
    0.14
    urally
    0.14
    HTTPHeader
    0.14
    ÑĢеменно
    0.14
    497
    0.14
    ORMAT
    0.13
    Act Density 0.012%

    No Known Activations