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

    Neuronpedia

    INDEX
    Explanations

    references to disciplinary actions and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.03
    Diweddarwch
    -0.95
    ">//
    -0.82
    gnac
    -0.80
    featureID
    -0.76
    InputTagHelper
    -0.76
    rrggbb
    -0.74
    WithIOException
    -0.71
    CPtr
    -0.66
    ETHING
    -0.66
    POSITIVE LOGITS
     disciplinary
    0.87
     discipl
    0.74
     punishable
    0.68
     punished
    0.64
     punishment
    0.63
     Discipline
    0.62
     Discipl
    0.61
     discipline
    0.61
     misdemeanor
    0.61
     penalties
    0.60
    Act Density 0.355%

    No Known Activations