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

    Neuronpedia

    INDEX
    Explanations

    references to personal accountability and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idious
    -0.16
    rous
    -0.15
     oft
    -0.13
     certain
    -0.13
    Âł
    -0.13
     Hod
    -0.12
    yne
    -0.12
    InputStream
    -0.12
    irl
    -0.12
    <Renderer
    -0.12
    POSITIVE LOGITS
    é¬
    0.16
    ully
    0.15
     Truy
    0.15
    ñas
    0.14
     å»
    0.14
    stime
    0.14
    oader
    0.14
    åĢij
    0.14
    endet
    0.14
    amina
    0.14
    Act Density 0.004%

    No Known Activations