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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate progress and project developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jak
    -0.15
    arter
    -0.15
     Freem
    -0.14
    491
    -0.13
    argins
    -0.13
    URED
    -0.13
     ong
    -0.13
    ằm
    -0.13
     escap
    -0.13
    avana
    -0.13
    POSITIVE LOGITS
    lah
    0.22
     accordingly
    0.19
    otos
    0.16
    EqualTo
    0.15
    imuth
    0.14
    ushman
    0.14
    apyrus
    0.14
     Tow
    0.13
    æĹ¢
    0.13
     Accordingly
    0.13
    Act Density 0.270%

    No Known Activations