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

    Neuronpedia

    INDEX
    Explanations

    a variety of situations or conditions that span a range or spectrum

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate variation or range among topics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rics
    -0.71
    driving
    -0.70
    bis
    -0.69
    idity
    -0.63
    士
    -0.58
    iquette
    -0.58
    jug
    -0.58
    talk
    -0.57
    IV
    -0.57
     Submission
    -0.56
    POSITIVE LOGITS
     ranging
    1.06
    ranging
    0.95
    ĸļ
    0.91
     between
    0.88
    Ĥª
    0.79
     wildly
    0.76
     upwards
    0.74
    efully
    0.74
    between
    0.73
     across
    0.73
    Act Density 0.039%

    No Known Activations