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

    Neuronpedia

    INDEX
    Explanations

    inquiries or questions regarding uncertainty or curiosity

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

    wondering if or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uestamente
    -0.61
     royaume
    -0.58
     houſe
    -0.54
    paravant
    -0.53
     démocr
    -0.52
    amentlich
    -0.51
    ſelf
    -0.51
    transQ
    -0.51
     namelijk
    -0.49
     operazioni
    -0.49
    POSITIVE LOGITS
     perhaps
    0.47
     curious
    0.45
     Wonder
    0.45
    wonder
    0.43
     wonder
    0.43
     ponder
    0.42
    curious
    0.41
     wondering
    0.40
    addington
    0.40
    perhaps
    0.40
    Act Density 0.015%

    No Known Activations