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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the abbreviation "MS" along with some numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to Multiple Sclerosis (MS) and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ========
    -0.69
    ãĤ©
    -0.66
     Judaism
    -0.63
     Hundred
    -0.61
    tained
    -0.60
     recalling
    -0.60
     joking
    -0.59
     Strauss
    -0.58
     communist
    -0.56
    ============
    -0.55
    POSITIVE LOGITS
    erver
    1.02
    ertodd
    0.99
    gt
    0.97
    mith
    0.92
    ettings
    0.90
    fw
    0.87
    MS
    0.85
    clerosis
    0.84
    ession
    0.83
    ync
    0.82
    Act Density 0.005%

    No Known Activations