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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "several"

    oai_token-act-pair · gpt-3.5-turbo

    blank or empty sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anything
    -0.81
    IAS
    -0.75
    istan
    -0.73
    ESE
    -0.73
    nothing
    -0.71
    asta
    -0.70
     thence
    -0.70
    thus
    -0.70
    doesn
    -0.69
    bas
    -0.68
    POSITIVE LOGITS
     hundred
    1.70
     dozen
    1.51
     thousand
    1.48
     occasions
    1.04
     aspects
    1.03
    teenth
    1.03
     months
    1.01
     times
    1.00
    dozen
    0.98
     weeks
    0.98
    Act Density 0.060%

    No Known Activations