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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dealing with challenges or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    articles and quantifiers like "a" and "lots."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.73
    %:
    -0.70
    Images
    -0.69
     Released
    -0.67
    antic
    -0.66
     unsurprisingly
    -0.66
     Shares
    -0.64
     Annotations
    -0.64
     additionally
    -0.63
     Amid
    -0.63
    POSITIVE LOGITS
     lot
    1.52
     bunch
    1.27
     guy
    1.19
     really
    1.17
     couple
    1.08
     little
    1.04
     tremendous
    1.02
     whole
    1.02
     pretty
    0.97
     very
    0.97
    Act Density 0.257%

    No Known Activations