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

    Neuronpedia

    INDEX
    Explanations

    phrases related to averages and specific or unique instances

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    PerformLayout
    -1.01
     שוליים
    -0.72
    脚注の使い方
    -0.69
     varandra
    -0.69
     Celui
    -0.67
    InstrumentedTest
    -0.67
    haikusbot
    -0.66
    antaranya
    -0.66
     FormBuilder
    -0.63
     enfance
    -0.63
    POSITIVE LOGITS
     qu
    0.57
     dé
    0.52
    dtd
    0.49
    ...
    0.47
    ricus
    0.47
     tro
    0.47
    aciones
    0.46
    сиона
    0.46
     Qu
    0.45
    mote
    0.45
    Act Density 0.108%

    No Known Activations