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

    Neuronpedia

    INDEX
    Explanations

    the word "semi" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "semi."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanto
    -0.78
    icators
    -0.65
     Curve
    -0.65
    bats
    -0.65
     Brooks
    -0.65
     Tycoon
    -0.64
     fingertips
    -0.64
     guts
    -0.62
    nia
    -0.61
     Lia
    -0.61
    POSITIVE LOGITS
    -)
    1.00
    lethal
    0.96
    -
    0.92
    -[
    0.88
    ature
    0.88
    -'
    0.87
     versa
    0.86
    atomic
    0.85
    ère
    0.85
    adic
    0.85
    Act Density 0.024%

    No Known Activations