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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values within a text

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the number "28" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achu
    -0.83
    allo
    -0.79
    reads
    -0.79
    amaru
    -0.78
    rophe
    -0.77
    algia
    -0.75
    ensibly
    -0.74
    ostics
    -0.74
    ĸļ
    -0.73
    rament
    -0.73
    POSITIVE LOGITS
    00
    1.04
    nm
    0.86
    th
    0.83
    80
    0.81
    iology
    0.80
    nd
    0.78
    mins
    0.74
     livest
    0.72
    GES
    0.68
    mph
    0.68
    Act Density 0.030%

    No Known Activations