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

    Neuronpedia

    INDEX
    Explanations

    indications of obligations or actions taken by individuals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    বহ
    -0.51
    weil
    -0.50
    DoubleQuotes
    -0.50
     ourselves
    -0.48
     SWE
    -0.48
    Bindable
    -0.47
    NOPQRST
    -0.46
    省市镇
    -0.46
    oire
    -0.45
     selves
    -0.45
    POSITIVE LOGITS
     Somebody
    0.79
    tagHelperRunner
    0.76
     whoſe
    0.76
     Whoever
    0.74
    Whoever
    0.71
     Quien
    0.71
    Somebody
    0.69
     Celui
    0.69
    Quien
    0.68
     Monfieur
    0.67
    Act Density 0.128%

    No Known Activations