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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty, emphasis, or definitive statements

    oai_token-act-pair · gpt-3.5-turbo

    words that express certainty or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mats
    -0.69
     Mant
    -0.68
     bount
    -0.65
     Mour
    -0.64
     Picks
    -0.62
     Kub
    -0.61
     Gran
    -0.61
     Rolls
    -0.61
    heads
    -0.61
     Wend
    -0.60
    POSITIVE LOGITS
     afford
    1.11
     imagine
    0.96
     conceive
    0.95
     withstand
    0.90
     muster
    0.88
    berra
    0.87
     survive
    0.86
     communicate
    0.82
     navigate
    0.82
     tolerate
    0.81
    Act Density 0.078%

    No Known Activations