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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "For" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrase constructions that introduce examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ownt
    -0.64
     deserves
    -0.62
    itiz
    -0.62
    izzle
    -0.57
     forg
    -0.56
     beg
    -0.56
    pron
    -0.56
    è¦ļéĨĴ
    -0.55
    illin
    -0.55
    Eat
    -0.55
    POSITIVE LOGITS
     example
    1.47
    cing
    1.31
     instance
    1.28
    gotten
    1.19
    bidden
    1.16
    ced
    1.16
     starters
    1.08
    got
    1.03
     comparison
    1.02
     Example
    1.00
    Act Density 0.060%

    No Known Activations