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

    Neuronpedia

    INDEX
    Explanations

    expressions of skepticism and reasoning in discussions about theories and research findings

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

    suggesting conjecture or assumption

    np_acts-logits-general · gemini-2.0-flash

    making assumptions or hypotheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    źć
    -0.49
    uolo
    -0.47
    aktery
    -0.47
     față
    -0.46
    ագրություններ
    -0.46
    didSet
    -0.45
    Itoa
    -0.45
    delaire
    -0.44
    ковь
    -0.43
    存于互联网档案馆
    -0.43
    POSITIVE LOGITS
     assumption
    1.91
     assume
    1.77
     supposition
    1.74
     assumptions
    1.74
     speculation
    1.72
     guesses
    1.72
     guessing
    1.68
     assumed
    1.68
     conjecture
    1.66
     guess
    1.65
    Act Density 0.822%

    No Known Activations