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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endregion
    -1.02
    ]--;
    -0.95
     STC
    -0.90
    MemoryWarning
    -0.86
     SSC
    -0.84
    ':{
    -0.84
    MDC
    -0.83
     cref
    -0.81
    endola
    -0.80
    iyle
    -0.78
    POSITIVE LOGITS
     UP
    1.43
     Up
    1.40
     up
    1.40
    AsUp
    1.36
    Up
    1.30
    up
    1.24
    UP
    1.21
    down
    0.99
     down
    0.98
     ups
    0.97
    Act Density 0.119%

    No Known Activations