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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities and statistics

    oai_token-act-pair · gpt-3.5-turbo

    statistics and data related to quantities and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.91
    ãĤ´ãĥ³
    -0.72
    çīĪ
    -0.70
    eln
    -0.64
     guise
    -0.62
    eatures
    -0.61
     sensibilities
    -0.60
    ĪĴ
    -0.59
    irlf
    -0.59
    awks
    -0.58
    POSITIVE LOGITS
     available
    0.82
     per
    0.81
     involved
    0.77
     consumed
    0.76
     surveyed
    0.75
     devoted
    0.73
     varies
    0.71
     required
    0.71
    izable
    0.71
     counted
    0.71
    Act Density 0.331%

    No Known Activations