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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their context within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omi
    -0.18
    ì§Ī
    -0.15
     Mah
    -0.14
    óng
    -0.14
    vox
    -0.13
    odi
    -0.13
    aqu
    -0.13
    виÑĩай
    -0.13
    ssi
    -0.13
    άνÏĦα
    -0.13
    POSITIVE LOGITS
    νοÏį
    0.16
     (%)
    0.13
    ب
    0.13
    ãĥ«ãĤ¯
    0.13
    /cloud
    0.13
    mach
    0.13
    perPage
    0.12
     (?)
    0.12
    cedes
    0.12
    fal
    0.12
    Act Density 0.107%

    No Known Activations