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

    Neuronpedia

    INDEX
    Explanations

    names of specific geographical locations or persons

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     shoulder
    -0.75
     acron
    -0.74
     hors
    -0.72
     RELE
    -0.71
     bureaucr
    -0.70
     initials
    -0.69
     prost
    -0.68
     circ
    -0.68
     puzz
    -0.68
     leg
    -0.67
    POSITIVE LOGITS
    aceae
    1.08
    ean
    1.06
    apest
    1.05
    ÃŃn
    1.03
    ipal
    1.02
    opol
    1.01
    opia
    1.00
    gettable
    1.00
    itsu
    0.99
    ois
    0.99
    Act Density 0.125%

    No Known Activations