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

    Neuronpedia

    INDEX
    Explanations

    URLs or specific website links

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     eleph
    -0.70
     bonding
    -0.64
     Sao
    -0.63
     IST
    -0.59
     jaws
    -0.59
     Cald
    -0.56
     ®
    -0.56
     flaw
    -0.55
     «
    -0.54
     uphill
    -0.54
    POSITIVE LOGITS
    /?
    1.42
    /
    1.42
    /_
    1.40
    /)
    1.40
    /,
    1.37
    /-
    1.25
    /#
    1.21
    /.
    1.17
    /"
    1.14
    \/
    1.07
    Act Density 0.065%

    No Known Activations