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

    Neuronpedia

    INDEX
    Explanations

    references to authors and citations in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.48
     document
    -0.47
    ucus
    -0.45
     error
    -0.45
    плу
    -0.45
     ato
    -0.44
     dos
    -0.44
     mode
    -0.44
     
    -0.43
     mé
    -0.43
    POSITIVE LOGITS
    ConstraintMaker
    1.05
    contentLoaded
    0.98
     estimés
    0.95
    ThroughAttribute
    0.92
     ProtoMessage
    0.87
    WebVitals
    0.86
     Egli
    0.81
    esModule
    0.80
    LookAnd
    0.80
     Lipschitz
    0.76
    Act Density 0.194%

    No Known Activations