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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships within a logical framework or model

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /−
    -0.85
    ".
    -0.82
    .)}
    -0.78
    )");
    -0.75
    saraba
    -0.75
    \<^
    -0.73
    — 
    -0.73
    leſs
    -0.73
     الدولى
    -0.73
    neſs
    -0.72
    POSITIVE LOGITS
     ,
    1.36
     .
    0.97
     ;
    0.94
    (),
    0.85
    <eos>
    0.83
    ().
    0.82
    ↵↵
    0.81
     ，
    0.79
     ،
    0.78
    .,
    0.75
    Act Density 0.961%

    No Known Activations