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

    Neuronpedia

    INDEX
    Explanations

    descriptions or explanations in a structured format, possibly in a technical or formal context

    oai_token-act-pair · gpt-3.5-turbo

    colons and text that indicates sections or subsections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulz
    -0.81
    rites
    -0.80
    undai
    -0.78
    uve
    -0.78
    ossip
    -0.75
    liction
    -0.72
    oser
    -0.71
    eatures
    -0.70
    inement
    -0.70
    anyl
    -0.69
    POSITIVE LOGITS
     Provided
    0.93
     Detected
    0.93
     Unknown
    0.82
     TBD
    0.82
     Impossible
    0.80
     Continued
    0.79
     Join
    0.78
     Contemporary
    0.78
     Programming
    0.78
     Originally
    0.78
    Act Density 0.098%

    No Known Activations