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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etooth
    -0.16
    landa
    -0.15
    aoke
    -0.15
    iger
    -0.15
    chwitz
    -0.15
    anuts
    -0.14
    piler
    -0.14
    engu
    -0.14
    olleyError
    -0.14
    IDGE
    -0.13
    POSITIVE LOGITS
    isos
    0.15
    itte
    0.13
    ool
    0.13
    osoph
    0.13
    REAM
    0.13
     Salisbury
    0.13
    hrad
    0.13
    _succ
    0.13
    stalk
    0.13
    elah
    0.13
    Act Density 0.160%

    No Known Activations