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

    Neuronpedia

    INDEX
    Explanations

    titles of books, movies, or historical events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the preposition "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eson
    -0.92
    ashtra
    -0.81
    ucci
    -0.78
     showc
    -0.77
    aciously
    -0.68
     diam
    -0.68
    respective
    -0.67
     versa
    -0.66
     formulations
    -0.65
    efully
    -0.65
    POSITIVE LOGITS
     Excellence
    1.08
     Inquiry
    0.91
     Instruction
    0.90
     Hate
    0.90
     Light
    0.86
     Hats
    0.86
     Transformation
    0.85
     Execution
    0.85
     Darkness
    0.85
     Grind
    0.84
    Act Density 0.112%

    No Known Activations