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

    Neuronpedia

    INDEX
    Explanations

    occurrences of certain letters or syllables in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kuk
    -0.15
    its
    -0.15
    +++
    -0.14
     ãĢī
    -0.14
    hib
    -0.14
    ë¶
    -0.14
    ully
    -0.14
    μή
    -0.14
    oven
    -0.14
    tings
    -0.13
    POSITIVE LOGITS
     tap
    0.18
    emmel
    0.17
     White
    0.16
     bread
    0.16
    rana
    0.15
    .opensource
    0.15
     Bread
    0.15
    ran
    0.14
    essel
    0.14
     Former
    0.14
    Act Density 0.014%

    No Known Activations