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

    Neuronpedia

    INDEX
    Explanations

    terms related to software and legal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endir
    -0.20
    adin
    -0.17
     w
    -0.16
    apore
    -0.16
     s
    -0.15
     mu
    -0.15
     Guns
    -0.14
     l
    -0.14
     y
    -0.14
     dummy
    -0.14
    POSITIVE LOGITS
    DataExchange
    0.18
    BOOLE
    0.16
    GenerationStrategy
    0.15
    ê²łëĭ¤
    0.15
    /Instruction
    0.15
    XObject
    0.15
    lacak
    0.15
    OptionsResolver
    0.14
    RuntimeObject
    0.14
    [section
    0.14
    Act Density 0.054%

    No Known Activations