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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey actions or events in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æīį
    -0.18
    ushman
    -0.15
     Jessica
    -0.15
    æīįèĥ½
    -0.15
    گاÙĨ
    -0.14
    885
    -0.14
     dual
    -0.14
     Mall
    -0.14
     wides
    -0.14
    زÙĦ
    -0.14
    POSITIVE LOGITS
     trata
    0.44
     tratt
    0.39
     trat
    0.33
     tr
    0.29
    tr
    0.29
     dealing
    0.28
    -tr
    0.28
     Tr
    0.28
    -Tr
    0.27
    .tr
    0.26
    Act Density 0.024%

    No Known Activations