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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and reflections shared in a conversational context

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

    Personal experiences or observations

    np_acts-logits-general · gemini-2.0-flash

    drawing conclusions from experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.78
     pleaſure
    -0.73
     Majefty
    -0.69
    majánló
    -0.68
     Reſ
    -0.67
     ſte
    -0.66
    parsedMessage
    -0.66
    featureID
    -0.66
     faſt
    -0.66
    adpleegd
    -0.66
    POSITIVE LOGITS
     observation
    0.41
     experience
    0.39
     tapasztal
    0.38
     observed
    0.36
     observations
    0.34
     constat
    0.32
     anecdotal
    0.31
     experiences
    0.31
     firsthand
    0.31
     trends
    0.31
    Act Density 0.270%

    No Known Activations