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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'everything' or comprehensive inclusivity in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     '',
    -0.76
     qu
    -0.75
     ‘
    -0.71
     any
    -0.69
     very
    -0.69
    ||}
    -0.69
    )|\
    -0.68
     "",
    -0.68
    ({
    -0.67
     small
    -0.65
    POSITIVE LOGITS
     itſelf
    1.02
     démission
    0.88
    IsContent
    0.86
     accompan
    0.86
     Thebes
    0.85
     Majefty
    0.85
     themſelves
    0.84
    UserScript
    0.83
     Piles
    0.82
     myſelf
    0.82
    Act Density 0.038%

    No Known Activations