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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal rulings and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Citations of court cases with a number followed by "d"

    np_acts-logits-general · gemini-2.0-flash

    legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diſ
    -0.95
     pleaſure
    -0.94
     ſtate
    -0.91
     raiſ
    -0.90
     CreateTagHelper
    -0.89
     fubject
    -0.85
     perfons
    -0.84
     myſelf
    -0.84
     Efq
    -0.83
     Majefty
    -0.83
    POSITIVE LOGITS
     h
    0.47
     super
    0.46
     "
    0.45
     a
    0.45
     '
    0.45
    Véxase
    0.44
     an
    0.44
     mu
    0.44
     _
    0.44
     del
    0.42
    Act Density 0.312%

    No Known Activations