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

    Neuronpedia

    INDEX
    Explanations

    descriptions of gourmet food and wine pairings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.16
    pra
    -0.15
    assel
    -0.15
    ække
    -0.14
    fortawesome
    -0.14
    ágina
    -0.14
    tti
    -0.14
    layan
    -0.14
    -caret
    -0.14
    ymax
    -0.14
    POSITIVE LOGITS
     structured
    0.23
     concentration
    0.23
     structure
    0.22
     plush
    0.22
     Cab
    0.22
     concentrated
    0.22
     sup
    0.21
     silky
    0.21
     extracted
    0.21
     Bordeaux
    0.21
    Act Density 0.016%

    No Known Activations