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

    Neuronpedia

    INDEX
    Explanations

    formatted strings and placeholders in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )");
    -1.18
    )');
    -0.95
    )";
    -0.93
    )");
    -0.93
    )++;
    -0.92
    PreferredItem
    -0.92
    ImageContext
    -0.91
    />";
    -0.89
    ]";
    -0.87
    !")
    -0.86
    POSITIVE LOGITS
     @
    0.55
     or
    0.51
    @
    0.51
     and
    0.50
     segn
    0.48
    ond
    0.46
    .
    0.45
    W
    0.44
     (
    0.44
    ,
    0.44
    Act Density 1.075%

    No Known Activations