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

    Neuronpedia

    INDEX
    Explanations

    terms related to reliability and consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Viewing
    -0.59
    Fizz
    -0.59
    Viewing
    -0.59
     Erb
    -0.58
    cipital
    -0.58
     springfox
    -0.58
    fxml
    -0.58
     Garvey
    -0.57
    טור
    -0.57
     Ricci
    -0.56
    POSITIVE LOGITS
     reliable
    1.54
    Reliable
    1.46
     Reliable
    1.43
    reliable
    1.34
     reliability
    1.34
     dependable
    1.31
     trustworthy
    1.29
     reliably
    1.29
     zuverläs
    1.23
     fiable
    1.20
    Act Density 0.137%

    No Known Activations