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

    Neuronpedia

    INDEX
    Explanations

    references to legislative hearings and testimonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.07
    4:0.09
    5:0.01
    6:0.03
    7:0.35
    8:0.03
    9:0.02
    10:0.14
    11:0.13
    Negative Logits
    RIP
    -1.40
    phrine
    -1.39
    edia
    -1.35
    ール
    -1.34
    fixed
    -1.29
     ashes
    -1.28
    irl
    -1.25
    blogspot
    -1.25
    dylib
    -1.24
    adish
    -1.24
    POSITIVE LOGITS
     recount
    1.49
     witnesses
    1.49
     eyewitness
    1.39
    itness
    1.36
    icken
    1.35
    oké
    1.32
     testimony
    1.31
     affidav
    1.31
     testifying
    1.31
    paio
    1.28
    Act Density 0.016%

    No Known Activations