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

    Neuronpedia

    INDEX
    Explanations

    the word "suited" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "su."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dayton
    -0.66
     bounce
    -0.62
     diminishing
    -0.62
     point
    -0.61
     frame
    -0.61
     trade
    -0.61
     Wheat
    -0.61
     percentage
    -0.60
     stationary
    -0.59
     plates
    -0.58
    POSITIVE LOGITS
    su
    4.54
    Su
    2.18
    SU
    1.53
     Su
    1.41
    suit
    1.40
    nir
    1.28
    suits
    1.20
    si
    1.17
     Tsu
    1.16
    shi
    1.14
    Act Density 0.015%

    No Known Activations