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

    Neuronpedia

    INDEX
    Explanations

    legal and court-related text

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

    references to legal or judicial terminology and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.32
    3:0.06
    4:0.10
    5:0.05
    6:0.03
    7:0.03
    8:0.04
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
     Guant
    -1.29
     Saras
    -1.26
    uador
    -1.25
     Veil
    -1.21
     Jinn
    -1.20
     Languages
    -1.17
    emies
    -1.11
     Philos
    -1.11
    ................
    -1.10
     Coral
    -1.09
    POSITIVE LOGITS
    issance
    1.66
    PAC
    1.45
    HM
    1.38
    backer
    1.37
    xus
    1.28
    uner
    1.27
    作
    1.23
    �
    1.23
    bard
    1.21
    street
    1.20
    Act Density 0.015%

    No Known Activations