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

    Neuronpedia

    INDEX
    Explanations

    references to parts or versions of articles or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.12
    2:0.05
    3:0.04
    4:0.03
    5:0.20
    6:0.04
    7:0.02
    8:0.14
    9:0.05
    10:0.05
    11:0.08
    Negative Logits
    phys
    -2.32
    achus
    -2.24
    eph
    -2.13
    eches
    -2.01
    phthal
    -2.01
    govtrack
    -1.99
    roph
    -1.96
    yg
    -1.96
    roleum
    -1.94
    hoe
    -1.91
    POSITIVE LOGITS
     timeline
    1.83
     date
    1.70
     slate
    1.67
     dialogue
    1.67
     timing
    1.64
     progression
    1.64
     inning
    1.61
     dates
    1.61
     Period
    1.61
     label
    1.56
    Act Density 0.001%

    No Known Activations