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

    Neuronpedia

    INDEX
    Explanations

    terms related to gathering or grouping things

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    thing
    -1.02
    req
    -0.99
    visor
    -0.91
    cffff
    -0.90
    lihood
    -0.89
    cgi
    -0.87
    ItemTracker
    -0.87
    wered
    -0.84
    ~~~~
    -0.84
     Centauri
    -0.83
    POSITIVE LOGITS
    umn
    1.31
    onel
    1.26
    ossus
    1.24
    iery
    1.23
    apsed
    1.23
    iseum
    1.15
     Kaepernick
    1.05
    ophon
    1.03
    abor
    1.01
    oqu
    1.00
    Act Density 2.175%

    No Known Activations