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

    Neuronpedia

    INDEX
    Explanations

    version numbers

    oai_token-act-pair · gpt-3.5-turbo

    the presence and referencing of version numbers in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undermin
    -0.72
     intimidation
    -0.70
     plaint
    -0.68
     purse
    -0.67
     discouraging
    -0.66
     waged
    -0.66
     evidenced
    -0.65
     rhet
    -0.63
     explan
    -0.63
     buck
    -0.63
    POSITIVE LOGITS
    0
    1.79
    6
    1.48
    5
    1.45
    7
    1.43
    4
    1.43
    3
    1.41
    9
    1.41
    1
    1.41
    2
    1.40
    8
    1.38
    Act Density 0.030%

    No Known Activations