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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators and notation used in formal definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.78
    D
    -0.74
     K
    -0.74
    i
    -0.74
    d
    -0.73
    S
    -0.72
    K
    -0.72
    l
    -0.71
     Men
    -0.71
    z
    -0.70
    POSITIVE LOGITS
     myſelf
    1.58
     Jefus
    1.44
    ſelves
    1.43
     pleaſure
    1.43
     themſelves
    1.40
     purpoſe
    1.38
     raiſ
    1.36
     himſelf
    1.32
     juſt
    1.29
     uſed
    1.29
    Act Density 0.792%

    No Known Activations