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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sequences or instructions involving steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uf
    -0.17
    (æľĪ
    -0.16
    erse
    -0.15
    app
    -0.15
    illa
    -0.14
    aise
    -0.14
    ÃŁ
    -0.13
    vox
    -0.13
    oha
    -0.13
    rak
    -0.13
    POSITIVE LOGITS
    asting
    0.15
    ittings
    0.14
    .googlecode
    0.14
    resco
    0.14
    forth
    0.14
    jar
    0.14
    ãģĵãģĿ
    0.14
    uder
    0.14
    çĵ
    0.13
    etal
    0.13
    Act Density 0.034%

    No Known Activations