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

    Neuronpedia

    INDEX
    Explanations

    exclamatory or expressive punctuation and phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terror began

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.79
    yarnpkg
    -0.66
     zwiſchen
    -0.65
     NSCoder
    -0.65
     oprot
    -0.65
    الإنجليزية
    -0.64
    ſicht
    -0.64
    -0.62
    wiliwch
    -0.62
    icoot
    -0.61
    POSITIVE LOGITS
     The
    0.40
    Already
    0.35
    The
    0.33
    neither
    0.33
    already
    0.33
    Neither
    0.33
    only
    0.32
    Even
    0.32
     Neither
    0.30
    almost
    0.30
    Act Density 0.007%

    No Known Activations