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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndum
    -0.81
    abase
    -0.78
    uthor
    -0.75
    alog
    -0.68
    xit
    -0.68
    ategory
    -0.68
    epad
    -0.66
    agonist
    -0.66
    ploy
    -0.65
    ovember
    -0.65
    POSITIVE LOGITS
     });
    0.62
    entimes
    0.61
     respectful
    0.60
     subscribing
    0.60
     Audrey
    0.59
     accordingly
    0.58
    Ń·
    0.57
     additionally
    0.57
    .'"
    0.57
     Safety
    0.56
    Act Density 0.069%

    No Known Activations