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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licity
    -0.15
    имо
    -0.15
    instead
    -0.14
    ogui
    -0.14
    omik
    -0.14
    ени
    -0.14
    anou
    -0.14
     his
    -0.13
    aes
    -0.13
     —↵↵
    -0.13
    POSITIVE LOGITS
     together
    0.36
     Together
    0.33
    Together
    0.29
     latter
    0.27
    äºĮ人
    0.21
     whom
    0.21
    who
    0.21
    ä¸Ģèµ·
    0.20
    gether
    0.20
     who
    0.20
    Act Density 0.047%

    No Known Activations