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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.74
     savage
    -0.73
    omics
    -0.73
    plet
    -0.71
    ought
    -0.69
     outraged
    -0.68
     instinct
    -0.66
     impression
    -0.66
     rallying
    -0.66
     morphed
    -0.65
    POSITIVE LOGITS
     Alternatively
    1.75
     Lastly
    1.73
     Additionally
    1.72
     Conversely
    1.70
     Likewise
    1.68
     Therefore
    1.65
     Similarly
    1.65
     Otherwise
    1.60
     Furthermore
    1.58
     However
    1.54
    Act Density 0.244%

    No Known Activations