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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and criminal justice terms and procedures

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

    references to governmental or legal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.07
    3:0.09
    4:0.09
    5:0.08
    6:0.07
    7:0.07
    8:0.08
    9:0.09
    10:0.09
    11:0.07
    Negative Logits
     Civilization
    -1.51
    hap
    -1.44
    evil
    -1.42
    ugi
    -1.38
    cup
    -1.35
     beams
    -1.34
    erest
    -1.34
    orescence
    -1.32
    nih
    -1.32
     Biol
    -1.32
    POSITIVE LOGITS
    thumbnails
    1.58
     parity
    1.48
     Hyder
    1.43
     rotation
    1.40
     polic
    1.39
     kosher
    1.37
     willingness
    1.36
     Mald
    1.35
     decision
    1.33
     professionalism
    1.30
    Act Density 0.000%

    No Known Activations