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

    Neuronpedia

    INDEX
    Explanations

    question marks and various punctuation symbols indicating uncertainty or exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑı
    -0.17
    foundland
    -0.16
    -0.15
    edl
    -0.15
    sdale
    -0.15
    ed
    -0.14
    tempts
    -0.14
    emean
    -0.14
    .AI
    -0.14
    apan
    -0.13
    POSITIVE LOGITS
    rst
    0.16
    åı·
    0.15
     åı·
    0.15
    IGH
    0.15
     latter
    0.15
    igh
    0.14
     signs
    0.14
    ,:,
    0.14
    itor
    0.14
    yny
    0.14
    Act Density 0.164%

    No Known Activations