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

    Neuronpedia

    INDEX
    Explanations

    terms related to qualitative descriptions or judgments about people, situations, or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulp
    -0.17
    allon
    -0.15
    oden
    -0.14
    837
    -0.14
    ÑĢован
    -0.13
     Fucking
    -0.13
    atively
    -0.13
    оди
    -0.13
    443
    -0.13
    831
    -0.13
    POSITIVE LOGITS
     ones
    0.39
     Ones
    0.30
    ones
    0.27
     stuff
    0.26
     Stuff
    0.22
    iest
    0.21
     portion
    0.20
    stuff
    0.20
    éĥ¨åĪĨ
    0.20
    liest
    0.18
    Act Density 0.167%

    No Known Activations