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

    Neuronpedia

    INDEX
    Explanations

    various forms and contexts of the word "feedback."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     battre
    -0.74
     Dyer
    -0.72
    Parcelize
    -0.69
     ro
    -0.65
     Byers
    -0.63
    istra
    -0.63
    ваны
    -0.63
     st
    -0.61
     mu
    -0.60
    malle
    -0.59
    POSITIVE LOGITS
     feedback
    2.46
    feedback
    2.14
     Feedback
    2.13
    Feedback
    1.99
     feedbacks
    1.97
     FEEDBACK
    1.82
    edback
    1.74
    FEEDBACK
    1.67
    反馈
    1.43
     pleaſure
    1.03
    Act Density 0.080%

    No Known Activations