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

    Neuronpedia

    INDEX
    Explanations

    comparisons and similarities between concepts or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SelectionMode
    -0.17
    amarin
    -0.16
    loggedin
    -0.16
    arendra
    -0.15
    amus
    -0.15
    averse
    -0.15
    isser
    -0.15
    540
    -0.14
    nown
    -0.14
    çŃĴ
    -0.14
    POSITIVE LOGITS
    ouce
    0.15
    nier
    0.15
    owers
    0.14
    icket
    0.14
    eldon
    0.14
     Niet
    0.14
    uced
    0.13
    uty
    0.13
    uly
    0.13
    uent
    0.13
    Act Density 0.234%

    No Known Activations