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

    Neuronpedia

    INDEX
    Explanations

    references to various types of identification and documentation numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "])
    -0.80
     '.';
    -0.71
     <<<<<<<<<<<<<<
    -0.70
    "):
    -0.69
     }}"></
    -0.68
    ]]
    -0.68
    "]);
    -0.68
    wiſe
    -0.68
    "]];
    -0.67
    )";
    -0.67
    POSITIVE LOGITS
     number
    0.87
    number
    0.73
     NUMBER
    0.69
     numbers
    0.68
     Number
    0.67
     name
    0.63
     code
    0.60
     номер
    0.60
    Hentet
    0.58
     anum
    0.58
    Act Density 0.348%

    No Known Activations