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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms related to various systems or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    en
    -0.24
    ens
    -0.22
    et
    -0.20
    ey
    -0.20
    erville
    -0.18
    enh
    -0.18
    ure
    -0.18
    ex
    -0.17
    aire
    -0.17
    a
    -0.17
    POSITIVE LOGITS
    naments
    0.22
    er
    0.21
    ourke
    0.21
    iginal
    0.19
    hythm
    0.19
    lando
    0.19
    haps
    0.18
    anged
    0.18
    erro
    0.18
    erer
    0.18
    Act Density 0.318%

    No Known Activations