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

    Neuronpedia

    INDEX
    Explanations

    words related to legal documents and investigations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    legal documents or references to affidavits in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.07
    2:0.09
    3:0.06
    4:0.07
    5:0.09
    6:0.06
    7:0.04
    8:0.06
    9:0.26
    10:0.07
    11:0.04
    Negative Logits
    ahime
    -1.87
    ゼウス
    -1.61
    iets
    -1.58
    paces
    -1.42
    aceae
    -1.39
    nuclear
    -1.35
    advant
    -1.35
    istas
    -1.32
    Europe
    -1.32
    essel
    -1.31
    POSITIVE LOGITS
     affidavit
    2.01
     affidav
    1.82
    idav
    1.75
     petitioner
    1.59
     confidential
    1.56
     redacted
    1.53
    ewitness
    1.50
    tained
    1.46
     particulars
    1.44
     receipts
    1.44
    Act Density 0.005%

    No Known Activations