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

    Neuronpedia

    INDEX
    Explanations

    frequent grammatical elements or functional words in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.21
    odzi
    -0.18
    zent
    -0.16
    èŃľ
    -0.16
    lamaz
    -0.15
    ÂŃi
    -0.15
     Há»
    -0.15
    inspace
    -0.15
    allah
    -0.15
    393
    -0.15
    POSITIVE LOGITS
     pur
    0.18
     F
    0.16
    974
    0.16
     tar
    0.16
    umb
    0.15
    çŁ¢
    0.15
     driver
    0.15
    ent
    0.15
    as
    0.14
    asp
    0.14
    Act Density 0.003%

    No Known Activations