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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the concept of "whole" or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aniston
    -0.74
     Shapiro
    -0.74
     Bekasi
    -0.70
    ीय
    -0.68
     Pittman
    -0.66
     Ganes
    -0.66
    Aziz
    -0.66
    iliano
    -0.64
     neutrinos
    -0.64
     Tapatalk
    -0.64
    POSITIVE LOGITS
     whole
    2.17
    whole
    2.17
    Whole
    2.14
     Whole
    2.07
     WHOLE
    1.93
     entire
    1.34
     whol
    1.29
     wholes
    1.25
     ganze
    1.12
     ganzen
    1.12
    Act Density 0.047%

    No Known Activations