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

    Neuronpedia

    INDEX
    Explanations

    instances of acknowledgment or recognition in narratives

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

    this is a response

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences that express opinions, evaluations, recommendations, or other subjective judgments.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     muß
    -0.66
     skall
    -0.63
     daß
    -0.57
     deleteAll
    -0.56
     quelquefois
    -0.56
     Moslem
    -0.54
     läßt
    -0.53
     müßte
    -0.49
     mußten
    -0.47
    いろいろな
    -0.47
    POSITIVE LOGITS
     incentiv
    0.81
     underwhelming
    0.73
     nuanced
    0.71
     mentorship
    0.71
    Alright
    0.69
     impactful
    0.68
     anyways
    0.68
     prioritize
    0.68
     timelines
    0.67
     estekak
    0.66
    Act Density 0.232%

    No Known Activations