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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or sequences containing names or alphanumeric patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )");
    -0.78
    RUnlock
    -0.76
     بيها
    -0.74
     للمعارف
    -0.74
    ()")
    -0.73
     }}$}
    -0.72
    ')")
    -0.72
    !")
    -0.71
    CppCodeGen
    -0.71
    .)}
    -0.70
    POSITIVE LOGITS
    XXX
    0.85
    XYZ
    0.85
     XYZ
    0.84
    xxx
    0.82
     XXX
    0.80
     xxx
    0.79
    XX
    0.76
    xx
    0.73
     xyz
    0.70
     xx
    0.69
    Act Density 0.269%

    No Known Activations