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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computers and programming

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to computing and networking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     theirs
    -0.59
    .}
    -0.58
     âĢİ
    -0.58
     .)
    -0.57
    .).
    -0.57
    efully
    -0.55
    wit
    -0.55
    Nut
    -0.54
     hers
    -0.54
    $.
    -0.54
    POSITIVE LOGITS
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    0.67
     guiName
    0.67
     Compl
    0.56
    è¦ļéĨĴ
    0.55
     Sapp
    0.50
     Fail
    0.50
     Photograph
    0.49
    ĵĺ
    0.49
    £ı
    0.49
     Breat
    0.49
    Act Density 1.018%

    No Known Activations