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

    Neuronpedia

    INDEX
    Explanations

    phrases related to probationary sentences and legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.07
    3:0.06
    4:0.11
    5:0.02
    6:0.02
    7:0.38
    8:0.02
    9:0.03
    10:0.12
    11:0.07
    Negative Logits
    NetMessage
    -2.48
    govtrack
    -1.72
     applause
    -1.59
    zi
    -1.57
    田
    -1.57
     WATCHED
    -1.55
    Spread
    -1.50
    ê
    -1.49
    PsyNetMessage
    -1.45
     hoop
    -1.44
    POSITIVE LOGITS
     probation
    2.01
     Discipline
    1.62
     Centauri
    1.48
    etheless
    1.48
     Jupiter
    1.48
     reinstated
    1.42
     1952
    1.38
     perjury
    1.38
     parole
    1.38
     Correctional
    1.37
    Act Density 0.001%

    No Known Activations