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

    Neuronpedia

    INDEX
    Explanations

    commands related to software and technical activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    actor
    -0.73
    tymology
    -0.68
    kowski
    -0.64
    ging
    -0.59
     sentimental
    -0.59
    umbai
    -0.58
     traff
    -0.58
    aft
    -0.56
    faced
    -0.56
    western
    -0.56
    POSITIVE LOGITS
     session
    0.90
    ansion
    0.89
    UAL
    0.88
    ually
    0.87
    uality
    0.84
    nikov
    0.83
    ional
    0.82
     sessions
    0.81
     Session
    0.77
    ickr
    0.76
    Act Density 6.950%

    No Known Activations