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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal structures or health and dietary factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     J
    -1.02
     S
    -0.99
     O
    -0.97
     Z
    -0.93
     K
    -0.92
     E
    -0.92
     T
    -0.92
     o
    -0.91
    O
    -0.90
     she
    -0.88
    POSITIVE LOGITS
     myſelf
    1.68
     themſelves
    1.65
     Theſe
    1.61
     itſelf
    1.59
     purpoſe
    1.55
     Monfieur
    1.55
     pleaſure
    1.53
     Efq
    1.48
     faſt
    1.47
     ſeveral
    1.45
    Act Density 0.472%

    No Known Activations