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

    Neuronpedia

    INDEX
    Explanations

    quotations within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     derby
    -0.70
     Alger
    -0.68
     photography
    -0.66
     blogging
    -0.65
     affiliate
    -0.65
     Ross
    -0.64
     tabloid
    -0.64
     Stephenson
    -0.64
     Hayward
    -0.64
     publishing
    -0.63
    POSITIVE LOGITS
    almost
    1.08
    probably
    1.07
    doesn
    1.06
    every
    1.05
    too
    1.04
    whose
    1.04
    absolutely
    1.04
    never
    1.04
    could
    1.04
    completely
    1.03
    Act Density 0.098%

    No Known Activations