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

    Neuronpedia

    INDEX
    Explanations

    references to testing and hypotheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    клопе
    -0.76
     Farina
    -0.73
    ankind
    -0.69
     Backbone
    -0.68
    ORIAL
    -0.68
    Laptop
    -0.67
    ILIO
    -0.66
    Backbone
    -0.65
    SPIRE
    -0.64
     kür
    -0.64
    POSITIVE LOGITS
     tests
    1.64
     test
    1.58
     Tests
    1.54
     TEST
    1.51
     testing
    1.44
     Test
    1.44
    Tests
    1.38
    test
    1.37
    TEST
    1.37
     tested
    1.36
    Act Density 0.149%

    No Known Activations