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

    Neuronpedia

    INDEX
    Explanations

    terms related to loading or processing data or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to computational load or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.71
    SHIP
    -0.70
    vous
    -0.67
    icho
    -0.63
    Lind
    -0.63
    berra
    -0.63
    cussion
    -0.62
    chedel
    -0.62
    kos
    -0.62
    gary
    -0.60
    POSITIVE LOGITS
     load
    1.21
     loads
    1.19
    load
    1.01
    loads
    1.00
     Load
    0.97
    Load
    0.89
    iless
    0.85
    loading
    0.85
     loader
    0.84
    enger
    0.83
    Act Density 0.008%

    No Known Activations