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

    Neuronpedia

    INDEX
    Explanations

    general references to "things" or "stuff."

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

    The token "things" or a synonym of "things."

    np_acts-logits-general · gemini-2.0-flash

    things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.67
     EconPapers
    -0.63
    ⓧ
    -0.55
    autorest
    -0.54
     laſſen
    -0.53
     térmico
    -0.52
    Cyfarwyddwr
    -0.51
    expandindo
    -0.51
    AutoScale
    -0.50
    parsedMessage
    -0.50
    POSITIVE LOGITS
     things
    0.84
     Thing
    0.81
     thing
    0.81
    things
    0.80
     THINGS
    0.80
     Things
    0.78
    Thing
    0.76
    Things
    0.75
     THING
    0.74
     happening
    0.72
    Act Density 0.112%

    No Known Activations