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

    Neuronpedia

    INDEX
    Explanations

    the word "don't" or "don" followed by an apostrophe and "t"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "if you don't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Advice
    -0.74
     newcom
    -0.70
    vantage
    -0.66
    dar
    -0.64
     Individuals
    -0.63
     Casting
    -0.63
     Communities
    -0.62
     DRAGON
    -0.61
     Characters
    -0.60
    cised
    -0.60
    POSITIVE LOGITS
    't
    1.06
    ned
    0.91
    nit
    0.87
    NT
    0.82
    etsk
    0.81
    iet
    0.81
    ning
    0.78
    ÃŃ
    0.77
    nt
    0.77
    ners
    0.71
    Act Density 0.098%

    No Known Activations