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

    Neuronpedia

    INDEX
    Explanations

    materials or objects made of paper

    oai_token-act-pair · gpt-3.5-turbo

    references to paper and cardboard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivals
    -0.84
    cffffcc
    -0.84
    ostic
    -0.80
    CVE
    -0.77
    igious
    -0.77
    oise
    -0.76
    ostics
    -0.75
    akening
    -0.71
    «ĺ
    -0.71
    ideshow
    -0.70
    POSITIVE LOGITS
    clip
    1.27
     towels
    1.17
     towel
    0.97
    clips
    0.95
     pus
    0.92
    backs
    0.85
    thin
    0.85
    brush
    0.84
    maid
    0.82
    pee
    0.78
    Act Density 0.021%

    No Known Activations