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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to supporting, aiding, or assisting something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perhaps
    -0.71
    pants
    -0.71
     namely
    -0.70
    worth
    -0.69
     wherein
    -0.66
    govtrack
    -0.65
    ault
    -0.65
     aka
    -0.65
    replace
    -0.65
    Iterator
    -0.64
    POSITIVE LOGITS
     latter
    1.11
     wearer
    1.11
     same
    1.09
     remainder
    1.08
     entire
    1.07
     widest
    1.04
     entirety
    1.03
     aforementioned
    1.01
     fullest
    1.00
     largest
    0.98
    Act Density 0.361%

    No Known Activations