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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.80
     himſelf
    -0.77
     Monfieur
    -0.75
     Jefus
    -0.75
     myſelf
    -0.72
     useStyles
    -0.70
     Efq
    -0.69
    MigrationBuilder
    -0.69
     Inscrivez
    -0.68
     Cæsar
    -0.67
    POSITIVE LOGITS
    umably
    0.62
    ással
    0.59
     puis
    0.57
     or
    0.54
    antly
    0.51
     And
    0.51
     und
    0.51
     وخ
    0.51
     потом
    0.50
    ながら
    0.50
    Act Density 0.191%

    No Known Activations