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

    Neuronpedia

    INDEX
    Explanations

    names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    names or words with a specific phonetic pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.83
    animous
    -0.82
    ertodd
    -0.77
    £ı
    -0.75
    s
    -0.75
    ilaterally
    -0.74
    psons
    -0.73
    okingly
    -0.72
    hops
    -0.71
    otos
    -0.71
    POSITIVE LOGITS
    bris
    0.84
    OPLE
    0.83
    erers
    0.80
    llo
    0.77
    uce
    0.76
    erer
    0.74
    bane
    0.71
    chnology
    0.71
    uve
    0.71
    ande
    0.71
    Act Density 0.033%

    No Known Activations