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

    Neuronpedia

    INDEX
    Explanations

    quantities or degrees of something, specifically focusing on the amount or size

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.83
    arna
    -0.75
    merce
    -0.72
     fixme
    -0.71
    ãĤ
    -0.70
    mingham
    -0.70
    çīĪ
    -0.70
    ãĥ¡
    -0.68
    ãĤ©
    -0.66
    ãĤ¦ãĤ¹
    -0.65
    POSITIVE LOGITS
     allowable
    0.83
    scope
    0.76
     validity
    0.72
     composing
    0.71
     of
    0.69
     differential
    0.67
     extent
    0.66
     level
    0.66
     involved
    0.65
     amount
    0.65
    Act Density 0.171%

    No Known Activations