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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or questioning of existence

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

    Followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    quantifiers introducing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jambes
    -0.72
     decidedly
    -0.69
     genoux
    -0.65
     lèvres
    -0.60
     faisons
    -0.58
     admittedly
    -0.58
     épaules
    -0.57
     ostensibly
    -0.56
    roughly
    -0.55
     gleaned
    -0.54
    POSITIVE LOGITS
     equipments
    0.97
     evidences
    0.94
     stuffs
    0.88
     advices
    0.87
     researches
    0.83
     feedbacks
    0.80
     matured
    0.72
     softwares
    0.71
     informations
    0.71
     kind
    0.71
    Act Density 0.428%

    No Known Activations