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

    Neuronpedia

    INDEX
    Explanations

    specific trends, actions, or statements that indicate importance or relevance in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etag
    -0.18
    PTR
    -0.15
    одÑĭ
    -0.15
    wers
    -0.15
    .Utc
    -0.14
    -transitional
    -0.14
     ngh
    -0.14
    æ¸
    -0.14
    leh
    -0.13
    ái
    -0.13
    POSITIVE LOGITS
    glob
    0.15
     typeid
    0.15
    -www
    0.15
    efined
    0.15
    Ðĭ
    0.14
    assel
    0.13
    GLOSS
    0.13
    arken
    0.13
     Gott
    0.13
    alars
    0.13
    Act Density 0.010%

    No Known Activations