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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¸
    -0.17
     â
    -0.17
    acy
    -0.15
     Â
    -0.14
    i
    -0.14
    uw
    -0.14
    iod
    -0.14
    iche
    -0.14
     again
    -0.13
    :
    -0.13
    POSITIVE LOGITS
    ãĢĢ
    0.21
    0.21
    alian
    0.19
    ãĢĢ
    0.18
    ãĢĢl
    0.17
    ãĢĢV
    0.16
    [rand
    0.16
    ÑģÑĥÑĤ
    0.15
    ãĢĢãĤ¤
    0.15
    ãĢĢi
    0.15
    Act Density 0.912%

    No Known Activations