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

    Neuronpedia

    INDEX
    Explanations

    words related to mats or surfaces

    oai_token-act-pair · gpt-3.5-turbo

    references to "mat" or "mats."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.77
    ngth
    -0.71
    vous
    -0.70
     Tone
    -0.65
    FUL
    -0.64
    IDES
    -0.63
     exh
    -0.62
    FINE
    -0.61
    FAULT
    -0.60
    ordinate
    -0.60
    POSITIVE LOGITS
    hematically
    1.35
    rices
    1.28
     mat
    1.12
    urity
    1.05
    hemat
    1.04
    robat
    0.95
    ially
    0.93
    hematic
    0.92
    aroo
    0.91
    imes
    0.90
    Act Density 0.002%

    No Known Activations