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

    Neuronpedia

    INDEX
    Explanations

    positive expressions of preference or enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.15
    que
    -0.15
    uality
    -0.14
    ulen
    -0.14
    exit
    -0.14
    ign
    -0.14
    iners
    -0.13
     ÄIJá»
    -0.13
    Cab
    -0.13
    µ¬
    -0.13
    POSITIVE LOGITS
    unker
    0.17
    ledged
    0.16
    than
    0.14
    /lo
    0.14
    etros
    0.13
    erre
    0.13
     tslib
    0.13
    æŃ¡
    0.13
    ernal
    0.13
     INTERVAL
    0.13
    Act Density 0.046%

    No Known Activations