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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡t
    -0.16
    legen
    -0.16
    aclass
    -0.16
    inspace
    -0.15
    utow
    -0.15
    .Generated
    -0.15
    $LANG
    -0.15
    TRGL
    -0.15
    loat
    -0.14
    velope
    -0.14
    POSITIVE LOGITS
    i
    0.25
    er
    0.24
    s
    0.23
    ed
    0.23
    y
    0.22
    o
    0.20
    a
    0.19
    an
    0.19
    al
    0.19
    zelf
    0.18
    Act Density 0.147%

    No Known Activations