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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical processes and documentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EXTRACT
    -0.72
     Finlay
    -0.67
    inflater
    -0.62
     Sait
    -0.62
     Reverso
    -0.62
    Nadia
    -0.61
    tings
    -0.60
     sinh
    -0.60
     Prag
    -0.60
     Absor
    -0.60
    POSITIVE LOGITS
    >",
    0.71
     />";
    0.71
    ']")
    0.70
     />';
    0.68
    *]
    0.67
    }],
    0.67
    ">'.$
    0.66
    ";}
    0.65
    Robotics
    0.65
    /></
    0.64
    Act Density 0.322%

    No Known Activations