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

    Neuronpedia

    INDEX
    Explanations

    examples of measurements and comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.65
    PhysRev
    -0.59
    éndolo
    -0.58
    ModelSerializer
    -0.58
    dataclass
    -0.55
     MainAxisSize
    -0.55
     dė
    -0.52
    ワイイ
    -0.52
     fairer
    -0.51
     dettaglio
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.69
     demonstration
    0.65
     demostr
    0.64
     demonstrating
    0.62
     proof
    0.60
     showcase
    0.59
     test
    0.58
    Chham
    0.57
     illustrating
    0.57
     showcasing
    0.55
    Act Density 0.340%

    No Known Activations