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

    Neuronpedia

    INDEX
    Explanations

    phrases related to originality or uniqueness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    avorite
    -0.78
    pherd
    -0.77
    tics
    -0.67
    wat
    -0.64
    gregation
    -0.62
    endas
    -0.61
    athed
    -0.61
    mania
    -0.61
    morph
    -0.61
    âĶģ
    -0.61
    POSITIVE LOGITS
     place
    0.98
     baseman
    0.89
     installment
    0.86
     millennium
    0.85
     decade
    0.83
     iteration
    0.82
     instance
    0.82
     inning
    0.81
     phase
    0.78
     edition
    0.78
    Act Density 0.064%

    No Known Activations