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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of "whole" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whole
    -0.17
    intree
    -0.17
     whole
    -0.16
    ses
    -0.16
    Æ°á»Ľc
    -0.15
    inel
    -0.15
    jem
    -0.15
    нин
    -0.15
    light
    -0.14
     ç¸
    -0.14
    POSITIVE LOGITS
    heart
    0.31
    -hearted
    0.26
    -sale
    0.24
     host
    0.24
    meal
    0.22
    foods
    0.21
    /part
    0.20
    SA
    0.20
     different
    0.19
     lot
    0.19
    Act Density 0.024%

    No Known Activations