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

    Neuronpedia

    INDEX
    Explanations

    the word "then" occurring in sequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     rafra
    -0.77
     réve
    -0.76
     mû
    -0.72
     angelo
    -0.69
     Attr
    -0.68
     perpé
    -0.68
     monaster
    -0.67
     éta
    -0.66
     fons
    -0.66
     éto
    -0.65
    POSITIVE LOGITS
     then
    0.99
     THEN
    0.85
    then
    0.78
     subsequently
    0.76
     proceed
    0.74
     thereafter
    0.71
     afterwards
    0.71
     Then
    0.71
    Then
    0.70
    THEN
    0.69
    Act Density 0.108%

    No Known Activations