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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to legal penalties and sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.08
    3:0.14
    4:0.02
    5:0.06
    6:0.06
    7:0.09
    8:0.09
    9:0.22
    10:0.06
    11:0.07
    Negative Logits
    enhagen
    -1.44
    pit
    -1.26
    Texture
    -1.26
    chat
    -1.22
    bert
    -1.21
    soDeliveryDate
    -1.18
    wolves
    -1.16
    Vs
    -1.15
    ickets
    -1.15
    ampa
    -1.13
    POSITIVE LOGITS
     perjury
    1.50
     revocation
    1.46
     remission
    1.45
     inflic
    1.41
     expulsion
    1.41
     punishable
    1.40
     jurisdiction
    1.39
    hemy
    1.38
     penalties
    1.37
    xus
    1.32
    Act Density 0.001%

    No Known Activations