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

    Neuronpedia

    INDEX
    Explanations

    contractions that include "are" followed by an adjective

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the contraction "we're."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reduce
    -0.72
     mater
    -0.70
    ESE
    -0.69
    andise
    -0.68
     membr
    -0.63
    TAIN
    -0.62
    ={
    -0.61
    iates
    -0.60
    DS
    -0.60
    acters
    -0.59
    POSITIVE LOGITS
     gonna
    1.45
     gotta
    1.13
     hoping
    1.01
     going
    0.99
     supposed
    0.95
     guessing
    0.92
     afraid
    0.92
     glad
    0.91
     got
    0.90
     sorry
    0.88
    Act Density 0.068%

    No Known Activations