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

    Neuronpedia

    INDEX
    Explanations

    phrases related to staying informed or updated

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    furt
    -0.68
    »Ĵ
    -0.59
     Haram
    -0.56
     Triangle
    -0.56
     Kahn
    -0.54
     ACTIONS
    -0.54
    RAL
    -0.53
     Ing
    -0.53
     Rutherford
    -0.52
     Munich
    -0.52
    POSITIVE LOGITS
     appearances
    0.99
    dates
    0.74
    earances
    0.72
     pace
    0.71
     footing
    0.70
    steen
    0.66
    ency
    0.65
    dating
    0.65
     tabs
    0.64
    standing
    0.62
    Act Density 0.018%

    No Known Activations