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

    Neuronpedia

    INDEX
    Explanations

    references to character encodings and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otton
    -0.19
    emouth
    -0.17
    indle
    -0.17
    itia
    -0.16
    kan
    -0.15
    ænd
    -0.15
    actus
    -0.14
    amines
    -0.14
    qv
    -0.14
    holm
    -0.14
    POSITIVE LOGITS
    ehir
    0.17
    deaux
    0.14
    ога
    0.14
    eview
    0.14
    tah
    0.13
    £¨
    0.13
    redo
    0.13
    shiv
    0.13
    /scripts
    0.13
    ICO
    0.13
    Act Density 0.002%

    No Known Activations