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

    Neuronpedia

    INDEX
    Explanations

    formal language structures beginning with "As"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "As [subject]" indicating a contextual reference or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩ
    -0.68
    Ö¼
    -0.64
    pez
    -0.63
    ãģł
    -0.62
    ãģ®å®
    -0.62
    ||||
    -0.61
    âĹ¼
    -0.60
    ÙĴ
    -0.59
     whatsoever
    -0.59
    ISM
    -0.59
    POSITIVE LOGITS
    bestos
    1.38
    phalt
    1.35
    piring
    1.34
    semb
    1.28
    pects
    1.22
    piration
    1.11
    leep
    1.10
    semble
    1.07
    ymm
    1.07
    ynchronous
    1.04
    Act Density 0.072%

    No Known Activations