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

    Neuronpedia

    INDEX
    Explanations

    tokens related to the flow or connection of information, such as "to," "from," and certain programming terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Griffin
    -0.82
    BoxShadow
    -0.80
     a
    -0.78
    ')],
    -0.77
     the
    -0.76
     podjela
    -0.74
    %");
    -0.73
    FactoryBean
    -0.72
    initely
    -0.72
     "
    -0.72
    POSITIVE LOGITS
    WebVitals
    0.72
     feroit
    0.69
     enfans
    0.69
     Thebes
    0.68
     trypto
    0.65
     eſt
    0.65
    AsUp
    0.65
     Chriftian
    0.64
     femininos
    0.63
     elétrico
    0.63
    Act Density 0.707%

    No Known Activations