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

    Neuronpedia

    INDEX
    Explanations

    references to accuracy or correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     müſſen
    -0.79
     imagui
    -0.76
    <unused43>
    -0.75
    <unused23>
    -0.75
    <pad>
    -0.75
    <unused42>
    -0.75
    <unused51>
    -0.75
    <unused41>
    -0.75
    <unused17>
    -0.75
    <unused19>
    -0.75
    POSITIVE LOGITS
    <bos>
    0.69
    ()))
    0.65
    '))
    0.51
    "))
    0.50
     prints
    0.47
    ])),
    0.46
    ())).
    0.46
    ()])
    0.45
    ])
    0.45
     and
    0.45
    Act Density 0.942%

    No Known Activations