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

    Neuronpedia

    INDEX
    Explanations

    substrings or formatted variables within string patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.89
    ]");
    -0.85
    >");
    -0.82
    "):
    -0.82
    )");
    -0.80
    }');
    -0.79
     });
    -0.79
    )";
    -0.78
    \"");
    -0.78
    %");
    -0.77
    POSITIVE LOGITS
     disponibilités
    0.71
    НИК
    0.63
     aceptas
    0.61
    ⓘ
    0.60
     judiciales
    0.59
     Jahrgang
    0.58
    Tikang
    0.58
     endblock
    0.57
     logistique
    0.54
     necesar
    0.54
    Act Density 0.065%

    No Known Activations