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

    Neuronpedia

    INDEX
    Explanations

    numerical values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.09
    3:0.11
    4:0.10
    5:0.15
    6:0.04
    7:0.03
    8:0.10
    9:0.11
    10:0.08
    11:0.05
    Negative Logits
    issance
    -1.16
    ound
    -1.09
    Registered
    -1.08
    unta
    -1.07
    owered
    -1.05
    ocative
    -1.00
    rough
    -0.99
    uay
    -0.99
    atars
    -0.96
    ounded
    -0.96
    POSITIVE LOGITS
     nor
    1.28
     darts
    1.11
     aspirin
    1.07
     pills
    1.02
     qualifications
    0.97
     revelation
    0.95
     apologies
    0.94
     anymore
    0.93
     footnote
    0.93
     suicides
    0.91
    Act Density 0.005%

    No Known Activations