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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating government agencies or official departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.04
    4:0.05
    5:0.03
    6:0.35
    7:0.15
    8:0.03
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
     occasions
    -1.78
     occasion
    -1.76
     Ct
    -1.35
    days
    -1.33
    phrine
    -1.33
    uations
    -1.31
     neighbors
    -1.30
     pretext
    -1.29
     eve
    -1.26
     Egyptians
    -1.24
    POSITIVE LOGITS
    uty
    1.39
    Program
    1.35
     Bradley
    1.30
    ceptor
    1.26
    itan
    1.26
    IDA
    1.25
     Programming
    1.25
    ��
    1.22
    acid
    1.20
    itaire
    1.20
    Act Density 0.005%

    No Known Activations