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

    Neuronpedia

    INDEX
    Explanations

    acronyms associated with specific organizations or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    p
    -0.23
    et
    -0.23
    h
    -0.23
    oft
    -0.22
    um
    -0.22
    etto
    -0.22
    etic
    -0.21
    ide
    -0.20
    oi
    -0.20
    umar
    -0.20
    POSITIVE LOGITS
    weeney
    0.15
    bard
    0.15
    dain
    0.15
    ichni
    0.15
    izable
    0.14
    ajor
    0.14
    oriasis
    0.14
    glich
    0.14
    cribed
    0.14
    RS
    0.13
    Act Density 0.032%

    No Known Activations