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

    Neuronpedia

    INDEX
    Explanations

    terms related to exclusivity or single options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     individual
    -0.16
     Og
    -0.15
     number
    -0.15
     Anders
    -0.15
     uns
    -0.15
     something
    -0.15
    ÑĸÑĪ
    -0.15
    ocha
    -0.14
     anders
    -0.14
     hell
    -0.14
    POSITIVE LOGITS
     Alone
    0.29
     alone
    0.28
     seule
    0.26
    alone
    0.25
    -only
    0.22
     thôi
    0.22
    -alone
    0.21
     saja
    0.21
     seul
    0.21
     sole
    0.20
    Act Density 0.127%

    No Known Activations