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

    Neuronpedia

    INDEX
    Explanations

    temporal adverbs indicating frequency and sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.29
    3:0.08
    4:0.06
    5:0.03
    6:0.04
    7:0.10
    8:0.04
    9:0.06
    10:0.08
    11:0.12
    Negative Logits
     Dialogue
    -1.50
    otto
    -1.47
    "}
    -1.43
     MAD
    -1.42
    ipel
    -1.40
    ograms
    -1.38
    arta
    -1.38
     annex
    -1.34
     Helsinki
    -1.29
     superiority
    -1.28
    POSITIVE LOGITS
    ividual
    1.89
     predec
    1.64
    yip
    1.61
     hairs
    1.49
     sighting
    1.48
     occurrence
    1.46
    FTWARE
    1.44
    aple
    1.43
    uitous
    1.35
     Gad
    1.34
    Act Density 0.001%

    No Known Activations