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

    Neuronpedia

    INDEX
    Explanations

    names of specific places and people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.69
    tenance
    -0.68
     Staples
    -0.66
    cers
    -0.64
    croft
    -0.64
     minded
    -0.63
    sers
    -0.61
     outgoing
    -0.59
    ModLoader
    -0.58
     foremost
    -0.57
    POSITIVE LOGITS
    ebra
    1.37
    ombies
    1.25
    ombie
    1.24
    odiac
    1.23
    ERO
    1.22
    ooming
    1.20
    ealous
    1.17
    eros
    1.09
    iggurat
    1.07
    imbabwe
    1.03
    Act Density 0.373%

    No Known Activations