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

    Neuronpedia

    INDEX
    Explanations

    references to quantities, studies, and discussions related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EdgeInsets
    -0.66
     nào
    -0.64
     AssemblyTitle
    -0.59
     two
    -0.57
     twofold
    -0.56
     거
    -0.55
    ArgsConstructor
    -0.55
     dvou
    -0.55
    ↷
    -0.55
     Lech
    -0.52
    POSITIVE LOGITS
     including
    0.67
    NOPQRST
    0.59
     Viele
    0.59
     والك
    0.59
     many
    0.58
    들이
    0.57
    <tfoot>
    0.57
     MANY
    0.56
    μως
    0.55
    MANY
    0.54
    Act Density 0.479%

    No Known Activations