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

    Neuronpedia

    INDEX
    Explanations

    references to relative comparisons or relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸĻ
    -0.17
    uality
    -0.17
    nat
    -0.17
    ald
    -0.16
    ride
    -0.15
    ter
    -0.15
    aper
    -0.15
    ancial
    -0.15
    ess
    -0.15
    nos
    -0.15
    POSITIVE LOGITS
     humidity
    0.24
     relative
    0.24
    (relative
    0.23
     Relative
    0.22
    -relative
    0.21
    humidity
    0.20
     newcomer
    0.19
    OLUTE
    0.19
    relative
    0.19
    Hum
    0.18
    Act Density 0.026%

    No Known Activations