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

    Neuronpedia

    INDEX
    Explanations

    statistics and numbers related to various topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Fuck
    -0.75
    azo
    -0.72
    OK
    -0.71
    tnc
    -0.69
    uct
    -0.69
    ogo
    -0.68
    enter
    -0.68
    irie
    -0.67
    Shut
    -0.67
    iciary
    -0.66
    POSITIVE LOGITS
     employs
    1.06
     expects
    1.01
     enjoys
    1.00
     consequently
    0.99
     contributes
    0.98
     although
    0.97
     boasts
    0.95
     strives
    0.93
     possesses
    0.92
     relies
    0.92
    Act Density 0.429%

    No Known Activations