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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inee
    -0.17
    ndon
    -0.16
    ména
    -0.16
    кÑĥл
    -0.15
    anmar
    -0.15
    èİİ
    -0.15
    游
    -0.15
    stown
    -0.14
    alah
    -0.14
    uxt
    -0.14
    POSITIVE LOGITS
    opoulos
    0.20
    ner
    0.19
    acz
    0.19
    cz
    0.19
    inger
    0.18
    man
    0.18
    owitz
    0.18
    berg
    0.17
    lund
    0.17
    stein
    0.17
    Act Density 0.631%

    No Known Activations