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

    Neuronpedia

    INDEX
    Explanations

    contractions of "we are"

    oai_token-act-pair · gpt-3.5-turbo

    contractions, particularly "we're" and "I'm," indicating a focus on personal and collective statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.75
    andise
    -0.68
    iox
    -0.67
    odder
    -0.67
    TAIN
    -0.67
    \/
    -0.65
    DS
    -0.64
    ren
    -0.63
    æĪ¦
    -0.60
    Scroll
    -0.60
    POSITIVE LOGITS
     gonna
    1.41
     gotta
    1.13
     sorry
    1.05
     guessing
    0.98
     going
    0.97
     not
    0.97
     hoping
    0.95
     glad
    0.95
     afraid
    0.93
     supposed
    0.91
    Act Density 0.076%

    No Known Activations