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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal or ethical issues, such as accountability, diversity, and social responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of societal issues or injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cradle
    -0.67
     Trent
    -0.63
     glad
    -0.62
     trickle
    -0.62
     Bravo
    -0.61
     hub
    -0.61
     Alberto
    -0.60
     farewell
    -0.60
     frontline
    -0.59
    kefeller
    -0.59
    POSITIVE LOGITS
     Examples
    1.33
     preferably
    1.27
    usually
    1.24
     Usually
    1.21
    typically
    1.20
    Examples
    1.18
    often
    1.10
     Often
    1.03
     Generally
    1.03
    Often
    1.02
    Act Density 0.632%

    No Known Activations