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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating cooking durations or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.04
    3:0.06
    4:0.14
    5:0.03
    6:0.03
    7:0.17
    8:0.07
    9:0.06
    10:0.10
    11:0.23
    Negative Logits
     estimate
    -1.48
     deadline
    -1.45
     stockpile
    -1.43
     repair
    -1.33
     LIA
    -1.29
     amput
    -1.27
     tan
    -1.27
     yr
    -1.26
     Uniform
    -1.25
     division
    -1.25
    POSITIVE LOGITS
    Trivia
    1.58
    Reloaded
    1.57
    olitics
    1.56
    Vers
    1.54
    ectar
    1.50
    Interview
    1.49
     underrated
    1.47
    Notable
    1.42
    Berry
    1.42
    plugins
    1.42
    Act Density 0.001%

    No Known Activations