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

    Neuronpedia

    INDEX
    Explanations

    references to human traits or characteristics through numbers and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungan
    -0.15
    .protobuf
    -0.14
    -hook
    -0.14
    /tiny
    -0.14
    úi
    -0.13
     Stevenson
    -0.13
    ozÃŃ
    -0.13
    ená
    -0.13
     DISPATCH
    -0.13
    æĵ
    -0.13
    POSITIVE LOGITS
     typ
    0.17
    ont
    0.17
    Ont
    0.16
     specifics
    0.16
     ont
    0.16
    418
    0.16
     researched
    0.15
     substantial
    0.15
     bearer
    0.15
    Router
    0.15
    Act Density 0.039%

    No Known Activations