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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "I" and variations of document-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Net
    -0.16
    auer
    -0.16
    ellen
    -0.15
     Kurt
    -0.15
     Pett
    -0.15
    IFT
    -0.15
     Rays
    -0.15
     Cognitive
    -0.14
    net
    -0.14
     Net
    -0.14
    POSITIVE LOGITS
    iali
    0.15
    iag
    0.14
    ialog
    0.14
    loh
    0.14
    uais
    0.14
    ORIGINAL
    0.14
    IALIZ
    0.14
    ../../../../
    0.14
    _hard
    0.14
     '..',
    0.13
    Act Density 0.040%

    No Known Activations