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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and summations in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.66
    AndEndTag
    -0.66
    BeginContext
    -0.63
    antası
    -0.63
    ActionCreators
    -0.62
     ModelExpression
    -0.62
    writeFieldEnd
    -0.60
    SequentialGroup
    -0.59
    GIVEREF
    -0.59
    findpost
    -0.56
    POSITIVE LOGITS
     ter
    0.35
     does
    0.34
     Brant
    0.32
     solid
    0.31
     did
    0.31
    @[+][
    0.31
    ране
    0.31
     flux
    0.30
     ghost
    0.30
     sud
    0.30
    Act Density 0.556%

    No Known Activations