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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality and logical connections

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Yep
    -1.03
    Really
    -0.88
    Seriously
    -0.83
    Enlarge
    -0.82
    Thumbnail
    -0.81
    Pretty
    -0.80
    atron
    -0.79
    Yeah
    -0.78
    Wait
    -0.78
     Nope
    -0.77
    POSITIVE LOGITS
     deviations
    1.04
     embodiments
    1.00
     considerable
    0.91
     however
    0.89
     there
    0.89
     we
    0.87
     implementations
    0.86
     although
    0.85
     excessive
    0.85
     heterogeneity
    0.85
    Act Density 0.337%

    No Known Activations