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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis commonly expressed using repeated words

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intensity or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.80
     guiActiveUn
    -0.66
    tnc
    -0.66
    Deploy
    -0.65
    ãĤ´
    -0.64
    î
    -0.64
    %:
    -0.63
     Citiz
    -0.63
    Ô
    -0.62
    Export
    -0.62
    POSITIVE LOGITS
     REALLY
    1.34
     really
    1.29
    really
    1.24
     Really
    1.01
     uh
    0.99
     truly
    0.97
     um
    0.94
     genuinely
    0.88
    yip
    0.86
     honestly
    0.84
    Act Density 0.051%

    No Known Activations