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

    Neuronpedia

    INDEX
    Explanations

    patterns in regex expressions and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '"
    -0.67
    ’”
    -0.64
     <>",
    -0.62
    ”
    -0.60
    yordu
    -0.58
    ’
    -0.55
     cebolla
    -0.53
    ajiban
    -0.53
     gouttes
    -0.52
    U
    -0.51
    POSITIVE LOGITS
    }`;
    1.26
    }';
    1.13
    '){
    1.12
    '));
    1.11
    '},
    1.07
    _'.$
    1.07
    `;
    1.06
    ')){
    1.04
     '.$
    1.04
    .';
    1.03
    Act Density 0.134%

    No Known Activations