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

    Neuronpedia

    INDEX
    Explanations

    words indicating causation or reasoning

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

    Follows first-person pronouns and discourse markers

    np_acts-logits-general · gemini-2.0-flash

    i found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     („
    -0.71
     (“
    -0.67
     (‘
    -0.65
     “...
    -0.61
     Vám
    -0.61
     „
    -0.60
     “[
    -0.60
     ‘
    -0.59
     (!)
    -0.58
     ‘‘
    -0.56
    POSITIVE LOGITS
     uh
    0.83
     Uh
    0.71
    ,}
    0.70
     um
    0.68
    ,]
    0.68
     yeah
    0.67
    Portale
    0.66
     Okay
    0.66
     And
    0.65
     Yeah
    0.65
    Act Density 0.104%

    No Known Activations