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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "whole" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whole
    -0.18
    uren
    -0.15
    ists
    -0.15
    zan
    -0.15
    iji
    -0.15
    quelle
    -0.14
    chine
    -0.14
    orial
    -0.14
    jem
    -0.14
    fts
    -0.14
    POSITIVE LOGITS
     thing
    0.39
    heart
    0.30
     ench
    0.27
    thing
    0.26
     Thing
    0.26
    -hearted
    0.26
     she
    0.25
    -sale
    0.24
     deal
    0.23
     lot
    0.22
    Act Density 0.032%

    No Known Activations