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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.16
    tte
    -0.16
    issing
    -0.14
    ož
    -0.14
    ↵
    -0.14
    ķ
    -0.14
    ocular
    -0.14
    縮
    -0.13
    uy
    -0.13
    words
    -0.13
    POSITIVE LOGITS
     why
    0.17
     How
    0.17
    how
    0.17
     how
    0.16
     When
    0.16
    ditor
    0.16
    assin
    0.16
     Which
    0.16
     Why
    0.15
    why
    0.15
    Act Density 0.032%

    No Known Activations