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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a quantity or measurement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Seat
    -1.00
     Kor
    -0.95
     Gutenberg
    -0.89
     Frontier
    -0.88
    inates
    -0.88
     Mansion
    -0.88
    hra
    -0.88
     abdom
    -0.84
     Manor
    -0.84
     Phant
    -0.83
    POSITIVE LOGITS
     amounts
    1.29
     amount
    1.25
    encies
    1.14
    ngth
    1.13
     quantities
    1.05
    ume
    0.99
    pour
    0.95
    entially
    0.93
    ftime
    0.93
    ucha
    0.92
    Act Density 0.701%

    No Known Activations