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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "whole" or "entirety."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.78
    brücken
    -0.68
     estimat
    -0.67
     bacilli
    -0.66
     Brutus
    -0.64
     dci
    -0.63
     Platon
    -0.63
     pathologist
    -0.63
    apunov
    -0.62
    rrggbb
    -0.60
    POSITIVE LOGITS
     entire
    1.21
     whole
    1.15
    whole
    1.03
    Whole
    1.00
     Whole
    0.97
     WHOLE
    0.96
     thing
    0.94
     ENTIRE
    0.88
    entire
    0.88
    Entire
    0.88
    Act Density 0.061%

    No Known Activations