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

    Neuronpedia

    INDEX
    Explanations

    the word "up" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endregion
    -1.01
     SSC
    -0.90
     STC
    -0.88
     PSS
    -0.87
     cref
    -0.85
     Mote
    -0.84
     Hess
    -0.83
    endola
    -0.83
    MDC
    -0.81
    ]--;
    -0.81
    POSITIVE LOGITS
     up
    1.39
    AsUp
    1.35
     UP
    1.31
     Up
    1.31
    Up
    1.20
    up
    1.15
    UP
    1.11
     down
    0.90
    down
    0.87
     DOWN
    0.86
    Act Density 0.128%

    No Known Activations