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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or conjunctions used to connect phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.97
    ..
    -0.65
    。
    -0.63
    ].
    -0.61
    ).
    -0.57
    ".
    -0.55
     .
    -0.54
    ।
    -0.52
    ».
    -0.52
    $.
    -0.51
    POSITIVE LOGITS
    $")
    1.10
    )");
    1.05
    "},
    1.05
    '},
    1.03
     Мексичка
    1.03
    "):
    1.02
    $}}
    1.01
    }")
    1.00
     betweenstory
    0.98
    )";
    0.98
    Act Density 0.113%

    No Known Activations