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

    Neuronpedia

    INDEX
    Explanations

    references to different types of ropes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    rope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')";
    -0.52
    )';
    -0.51
    ibatis
    -0.47
    javax
    -0.45
    .');
    -0.45
    ]();
    -0.44
     Aniston
    -0.44
    ."));
    -0.43
    denza
    -0.43
    antiation
    -0.42
    POSITIVE LOGITS
     rope
    2.16
     Rope
    2.06
    Rope
    1.94
     ropes
    1.79
    rope
    1.49
     cuerda
    1.34
     corda
    1.29
     corde
    1.14
     cordes
    1.13
     Seil
    1.09
    Act Density 0.004%

    No Known Activations