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

    Neuronpedia

    INDEX
    Explanations

    instances of notation and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     +
    -0.59
    +
    -0.58
    )";
    -0.55
    ';
    -0.53
     *
    -0.52
    [];
    -0.51
    ;">
    -0.51
     [],
    -0.50
     passim
    -0.50
     betweenstory
    -0.50
    POSITIVE LOGITS
     coû
    0.62
    Datuak
    0.58
     bicchiere
    0.55
    englanniksi
    0.55
     détru
    0.53
     boire
    0.53
     ModelExpression
    0.53
    bladet
    0.52
     piedi
    0.52
     podjet
    0.52
    Act Density 0.160%

    No Known Activations