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

    Neuronpedia

    INDEX
    Explanations

    references to quantities and variations across categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     G
    -0.51
     A
    -0.49
     N
    -0.48
    leyin
    -0.48
    back
    -0.48
     getC
    -0.47
     can
    -0.47
    x
    -0.46
    ])){
    -0.46
     along
    -0.46
    POSITIVE LOGITS
     Majefty
    0.87
     pleaſure
    0.83
     myſelf
    0.81
    ſelf
    0.80
     purpoſe
    0.78
     Jefus
    0.77
    Portale
    0.76
    TagMode
    0.76
     doInBackground
    0.76
     <<<<<<<<<<<<<<
    0.75
    Act Density 1.039%

    No Known Activations