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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and corporate behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elson
    -0.15
    (formatter
    -0.14
    ari
    -0.13
    Ä©
    -0.13
    EMU
    -0.13
    amma
    -0.13
    hoe
    -0.13
    erland
    -0.13
    pis
    -0.12
    éªĮ
    -0.12
    POSITIVE LOGITS
    /trunk
    0.16
    ableObject
    0.14
    cedes
    0.14
    ombie
    0.14
     گر
    0.14
    ypi
    0.14
    ØŃص
    0.14
    ãĥ¬
    0.14
    дов
    0.14
     lẫn
    0.14
    Act Density 0.079%

    No Known Activations