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

    Neuronpedia

    INDEX
    Explanations

    references to "whole" or "entire" entities and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wholly
    -0.15
    絶
    -0.14
     toujours
    -0.14
     celkem
    -0.14
     propia
    -0.14
    .jasper
    -0.14
     fisse
    -0.14
     altogether
    -0.13
    inand
    -0.13
    pong
    -0.13
    POSITIVE LOGITS
     thing
    0.41
     spectrum
    0.30
    heart
    0.29
     ench
    0.29
    ties
    0.29
    thing
    0.28
     gam
    0.27
     length
    0.26
     process
    0.26
     range
    0.26
    Act Density 0.052%

    No Known Activations