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

    Neuronpedia

    INDEX
    Explanations

    references to assessments or evaluations of things as a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding tokens followed by "whole"

    np_acts-logits-general · gemini-2.0-flash

    entirety and wholeness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    čník
    -0.51
    del
    -0.41
    laszt
    -0.41
    issan
    -0.38
    lite
    -0.37
    ys
    -0.37
    ルー
    -0.37
    ồi
    -0.36
     th
    -0.36
    UrlResolution
    -0.35
    POSITIVE LOGITS
     whole
    2.75
    whole
    2.54
    Whole
    2.21
     WHOLE
    2.08
     Whole
    2.06
     entire
    1.67
     entirety
    1.60
     целом
    1.42
     Entire
    1.39
     Ganzen
    1.37
    Act Density 0.196%

    No Known Activations