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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to functionality and performance in computational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.75
    GenerationType
    -0.65
    inheritDoc
    -0.58
    ControllerAdvice
    -0.58
    ]=-
    -0.55
    łuż
    -0.54
    AndEndTag
    -0.54
    AddHtmlAttribute
    -0.53
    RTGC
    -0.52
    StreetMap
    -0.52
    POSITIVE LOGITS
     properly
    1.87
     correctly
    1.58
    properly
    1.51
     safely
    1.34
     successfully
    1.32
     Properly
    1.31
     correctement
    1.30
     efficiently
    1.28
     adequately
    1.25
     reliably
    1.25
    Act Density 0.606%

    No Known Activations