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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance or competition

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Associated
    -0.82
    ãĤ´ãĥ³
    -0.79
    Elsewhere
    -0.71
     guiActiveUn
    -0.70
    Detailed
    -0.70
    SourceFile
    -0.68
    Continue
    -0.64
    ãĥ¥
    -0.63
    Similarly
    -0.62
    MpServer
    -0.61
    POSITIVE LOGITS
     yeah
    1.25
     somew
    1.24
     I
    1.09
     we
    1.04
     nobody
    1.02
     yes
    0.99
     whenever
    0.98
     everybody
    0.93
     there
    0.91
     wow
    0.90
    Act Density 0.361%

    No Known Activations