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

    Neuronpedia

    INDEX
    Explanations

    transcripts and associated metadata related to documents or media segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.11
    2:0.07
    3:0.04
    4:0.04
    5:0.14
    6:0.09
    7:0.09
    8:0.09
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    represented
    -1.77
    aimon
    -1.66
    gdala
    -1.64
    pora
    -1.53
    byss
    -1.52
     meanwhile
    -1.47
    hedon
    -1.47
    conservancy
    -1.46
    gat
    -1.45
    gars
    -1.44
    POSITIVE LOGITS
     reader
    1.46
     photoc
    1.43
     delivery
    1.33
    �
    1.33
     takeoff
    1.33
     typew
    1.32
    ...]
    1.27
     transcripts
    1.23
     newsp
    1.22
    .")
    1.21
    Act Density 0.001%

    No Known Activations