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

    Neuronpedia

    INDEX
    Explanations

    numerical values accompanied by variations of the word "stainless"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurements and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.80
     conflic
    -0.75
    oshenko
    -0.74
    culus
    -0.70
    DEM
    -0.66
     adolesc
    -0.65
     notor
    -0.64
     shedding
    -0.64
    mitted
    -0.64
    opes
    -0.63
    POSITIVE LOGITS
    ĸļ
    0.88
    nard
    0.88
    ify
    0.86
    gt
    0.85
    alist
    0.84
    ard
    0.82
    ees
    0.82
    eur
    0.82
    arius
    0.82
    ified
    0.80
    Act Density 0.024%

    No Known Activations