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

    Neuronpedia

    INDEX
    Explanations

    technical commands and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of time, duration, or updates in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.31
     conclud
    -0.28
    ãĥ¼ãĥĨ
    -0.28
     Tanz
    -0.28
     Huck
    -0.27
     Vaugh
    -0.25
    vertisement
    -0.25
     meanwhile
    -0.25
     moreover
    -0.24
     rul
    -0.24
    POSITIVE LOGITS
    natureconservancy
    0.28
    externalActionCode
    0.23
    minecraft
    0.23
     pics
    0.23
     liking
    0.22
    tackle
    0.22
    Drive
    0.22
     diapers
    0.21
    ?),
    0.21
     cs
    0.21
    Act Density 6.511%

    No Known Activations