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

    Neuronpedia

    INDEX
    Explanations

    terms related to increases or upward trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the upward particle/morpheme, including its use standalone, in prepositional phrases, in phrasal verbs, and as part of compound words.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Negative Logits
    endregion
    -1.05
    MDC
    -0.83
     SSC
    -0.80
     STC
    -0.79
     cref
    -0.79
    iyle
    -0.77
    endola
    -0.76
    ]--;
    -0.75
    MemoryWarning
    -0.74
    Spoiler
    -0.74
    POSITIVE LOGITS
     UP
    1.41
    AsUp
    1.41
     Up
    1.34
     up
    1.31
    Up
    1.24
    UP
    1.19
    up
    1.17
     ups
    1.02
     Ups
    0.98
    Ups
    0.94
    Act Density 0.125%

    No Known Activations