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

    Neuronpedia

    INDEX
    Explanations

    words related to envelopes and items that are contained within envelopes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Titans
    -0.73
    ãĤ´ãĥ³
    -0.72
    anooga
    -0.71
    nesota
    -0.66
    utsche
    -0.65
    aldi
    -0.62
     Ath
    -0.62
     Texans
    -0.61
    Stars
    -0.60
     Osw
    -0.59
    POSITIVE LOGITS
    velop
    0.97
     envelope
    0.91
    eers
    0.85
    stakes
    0.85
    mble
    0.84
    nuts
    0.82
    ingly
    0.82
     envelop
    0.81
    erella
    0.74
    pread
    0.72
    Act Density 8.880%

    No Known Activations