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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.58
    :✨
    -0.50
    TargetException
    -0.46
    ArgsConstructor
    -0.46
    ValueStyle
    -0.45
    StructEnd
    -0.43
    lickr
    -0.43
     المعيارى
    -0.42
     nargin
    -0.42
    BibitemShut
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    0.47
     mentioning
    0.44
     puisqu
    0.42
     sowieso
    0.41
    <?
    0.40
    gadier
    0.40
     suffice
    0.39
     mídia
    0.39
    ip
    0.39
    rąg
    0.38
    Act Density 1.089%

    No Known Activations