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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cooking instructions and techniques

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate duration or cooking times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egu
    -0.77
    pour
    -0.76
    raid
    -0.75
    eri
    -0.72
    generation
    -0.71
    çīĪ
    -0.71
    gu
    -0.70
    urb
    -0.68
    foreseen
    -0.67
    audi
    -0.67
    POSITIVE LOGITS
     adulthood
    0.70
     eternity
    0.69
     someone
    0.68
     infinity
    0.68
     desired
    0.67
     they
    0.66
     Bones
    0.64
     satisfied
    0.64
     proven
    0.63
    zee
    0.63
    Act Density 0.027%

    No Known Activations