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

    Neuronpedia

    INDEX
    Explanations

    the beginning of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himo
    -0.91
    []
    -0.89
    ]--;
    -0.88
    ^(@)
    -0.86
     Efq
    -0.85
     Majefty
    -0.80
    цездатний
    -0.80
    )];
    -0.80
    */;
    -0.79
     Jefus
    -0.78
    POSITIVE LOGITS
     but
    1.09
     which
    0.96
     and
    0.85
     including
    0.84
     although
    0.83
     though
    0.71
     because
    0.69
     as
    0.69
     along
    0.69
     even
    0.69
    Act Density 1.079%

    No Known Activations