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

    Neuronpedia

    INDEX
    Explanations

    references to feedback in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     xa
    -0.66
     ro
    -0.59
     Parrish
    -0.59
     ton
    -0.59
     po
    -0.58
    xa
    -0.58
     country
    -0.57
     mule
    -0.57
    mule
    -0.57
    na
    -0.57
    POSITIVE LOGITS
     feedback
    1.52
    feedback
    1.42
     Feedback
    1.41
     feedbacks
    1.38
    Feedback
    1.30
     FEEDBACK
    1.26
    edback
    1.19
    FEEDBACK
    1.19
    Datuak
    1.11
     <=",
    1.10
    Act Density 0.006%

    No Known Activations