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

    Neuronpedia

    INDEX
    Explanations

    key actions and expressions related to justice and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.05
     pleaſure
    -0.98
     itſelf
    -0.92
     ſche
    -0.90
     iſt
    -0.88
     reaſon
    -0.88
     Monfieur
    -0.86
    verwijspagina
    -0.85
     ſeveral
    -0.84
    TagMode
    -0.84
    POSITIVE LOGITS
     
    0.49
     its
    0.47
    ho
    0.44
     exact
    0.44
    :
    0.43
     a
    0.43
    しまい
    0.43
     '
    0.42
     gas
    0.42
    @
    0.41
    Act Density 1.211%

    No Known Activations