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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical and structural information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Entered
    -0.64
     trout
    -0.58
     Starr
    -0.57
     wildlife
    -0.56
     Floyd
    -0.55
     Hogan
    -0.54
     rang
    -0.52
     snakes
    -0.52
     Lewis
    -0.51
     Linda
    -0.51
    POSITIVE LOGITS
    SourceFile
    0.99
    ãĤ¦ãĤ¹
    0.90
    ļéĨĴ
    0.78
    ãĤ´ãĥ³
    0.75
    Accessory
    0.73
    Ô
    0.72
    ãģ®ç
    0.71
    76561
    0.70
    ¶æ
    0.68
    ĵĺ
    0.68
    Act Density 1.105%

    No Known Activations