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

    Neuronpedia

    INDEX
    Explanations

    references to ingredients and methods used in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccoli
    -0.16
     fitte
    -0.15
    ritch
    -0.15
    995
    -0.15
    akedown
    -0.14
     Caul
    -0.14
    orget
    -0.14
    ault
    -0.14
    /ca
    -0.14
     Mushroom
    -0.14
    POSITIVE LOGITS
    rais
    0.27
     wal
    0.27
     rais
    0.26
     cand
    0.26
     crystall
    0.22
     bits
    0.22
     chopped
    0.22
     Wal
    0.20
     nuts
    0.20
     currents
    0.20
    Act Density 0.062%

    No Known Activations