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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a negative and the verb "t" (e.g. don't, can't, won't)

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "didn't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inia
    -0.76
     Reduced
    -0.67
     Groups
    -0.66
     Suff
    -0.64
     Compar
    -0.58
     Medium
    -0.58
    士
    -0.58
     arsen
    -0.57
    lain
    -0.57
     Alleg
    -0.57
    POSITIVE LOGITS
     bother
    1.02
     realise
    0.93
     hesitate
    0.90
     realize
    0.90
     dare
    0.87
    erest
    0.86
    want
    0.83
     survive
    0.80
     necessarily
    0.80
     comply
    0.78
    Act Density 0.081%

    No Known Activations