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

    Neuronpedia

    INDEX
    Explanations

    references to locations and dates within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.08
    2:0.07
    3:0.05
    4:0.02
    5:0.07
    6:0.10
    7:0.18
    8:0.07
    9:0.15
    10:0.07
    11:0.06
    Negative Logits
     supra
    -1.30
    below
    -1.25
    versive
    -1.22
     replay
    -1.22
    mentioned
    -1.17
     Euph
    -1.11
     Maximum
    -1.11
     testified
    -1.10
     Objects
    -1.07
    angelo
    -1.06
    POSITIVE LOGITS
    ANS
    1.74
    INESS
    1.50
    atform
    1.48
    PRESS
    1.46
     NEWS
    1.41
    ENG
    1.39
    wat
    1.36
    INGTON
    1.35
    ENS
    1.34
    heast
    1.31
    Act Density 0.016%

    No Known Activations