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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating parts or portions related to a whole

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     entire
    -0.99
     whole
    -0.96
     entirety
    -0.96
    whole
    -0.92
     full
    -0.90
    COMPLETE
    -0.87
     Entire
    -0.85
     COMPLETE
    -0.85
     ENTIRE
    -0.84
     complete
    -0.84
    POSITIVE LOGITS
    ised
    0.62
    Viki
    0.61
    TextHelper
    0.59
    RetentionPolicy
    0.57
     Snackbar
    0.56
    izing
    0.55
     refrigerated
    0.52
     MTN
    0.51
     à
    0.51
    TV
    0.50
    Act Density 0.030%

    No Known Activations