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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts and patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owards
    -0.16
     part
    -0.14
    -away
    -0.14
     oldukça
    -0.14
    lobals
    -0.14
    imore
    -0.13
     Extremely
    -0.13
    erta
    -0.13
     awhile
    -0.13
    such
    -0.12
    POSITIVE LOGITS
     if
    0.48
     though
    0.38
    	if
    0.28
     еÑģли
    0.26
    though
    0.26
     nếu
    0.26
     Though
    0.25
     If
    0.25
    Though
    0.23
     wenn
    0.23
    Act Density 0.132%

    No Known Activations