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

    Neuronpedia

    INDEX
    Explanations

    questions or requests for feedback or support

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    upuncture
    -0.73
    ensions
    -0.72
    unning
    -0.69
    irth
    -0.66
    onomous
    -0.66
    ename
    -0.66
    actic
    -0.65
    agog
    -0.63
    lass
    -0.63
    gly
    -0.63
    POSITIVE LOGITS
     pertaining
    0.87
     answered
    0.84
     regarding
    0.75
     questions
    0.74
     relating
    0.73
    naires
    0.71
     inqu
    0.69
     inquiries
    0.69
     surrounding
    0.68
    hooting
    0.68
    Act Density 0.792%

    No Known Activations