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

    Neuronpedia

    INDEX
    Explanations

    terms related to restrictions and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.08
     itſelf
    -1.01
     purpoſe
    -1.00
     Jefus
    -0.98
     himſelf
    -0.98
     faſt
    -0.98
     Monfieur
    -0.97
     ſche
    -0.96
     pleaſure
    -0.95
     Theſe
    -0.93
    POSITIVE LOGITS
     P
    0.62
     (
    0.58
     S
    0.55
     M
    0.52
     .
    0.50
     for
    0.50
     W
    0.49
     U
    0.49
     B
    0.48
     L
    0.48
    Act Density 1.002%

    No Known Activations