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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dashes, indicating breaks or pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.05
    )";
    -0.88
     EconPapers
    -0.87
    NUMX
    -0.86
    )");
    -0.85
    .")
    -0.85
    `;
    -0.85
    archiviato
    -0.84
     ]
    -0.84
     Houſe
    -0.84
    POSITIVE LOGITS
    v
    0.62
     ~
    0.60
    un
    0.58
    it
    0.57
    _
    0.55
    !!
    0.54
    y
    0.54
     +
    0.54
     :
    0.53
     however
    0.53
    Act Density 0.135%

    No Known Activations