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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and ending symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.60
    ondy
    -0.58
     Franken
    -0.58
    häng
    -0.56
    brunnen
    -0.56
     Ani
    -0.54
    了口气
    -0.54
     Balas
    -0.53
     Aline
    -0.53
    ConstraintLayout
    -0.53
    POSITIVE LOGITS
    $;
    1.01
    ParallelGroup
    0.98
    AndEndTag
    0.93
     <=",
    0.87
    WriteLiteral
    0.85
    .;
    0.85
     propOrder
    0.85
    ;
    0.84
    __;
    0.84
    }$;
    0.84
    Act Density 0.161%

    No Known Activations