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

    Neuronpedia

    INDEX
    Explanations

    suffixes related to past actions and participles, particularly those involving the word "trump."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.05
    4:0.17
    5:0.03
    6:0.07
    7:0.33
    8:0.04
    9:0.04
    10:0.05
    11:0.07
    Negative Logits
    ーク
    -1.59
    ocamp
    -1.55
    mble
    -1.52
    imgur
    -1.48
    rio
    -1.43
    lique
    -1.36
    Veter
    -1.36
    sted
    -1.35
    spot
    -1.34
    flix
    -1.34
    POSITIVE LOGITS
     veto
    1.65
     arguments
    1.59
     possibilities
    1.47
     obstacles
    1.43
     abstraction
    1.42
     distractions
    1.42
     Brill
    1.41
     voices
    1.40
     extinction
    1.39
     interpretations
    1.36
    Act Density 0.001%

    No Known Activations