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

    Neuronpedia

    INDEX
    Explanations

    affirmations or confirmations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.83
    */;
    -0.65
    ...')
    -0.63
    seamnă
    -0.60
    UnsafeEnabled
    -0.59
     myſelf
    -0.59
    )";
    -0.59
    IndentedString
    -0.59
    ...');
    -0.57
     himſelf
    -0.57
    POSITIVE LOGITS
    ?
    0.72
    ?>
    0.59
    estacks
    0.57
    fao
    0.55
    ?)
    0.55
    ?).
    0.54
    Viited
    0.53
    !(:
    0.52
    fiq
    0.52
    armament
    0.52
    Act Density 0.065%

    No Known Activations