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

    Neuronpedia

    INDEX
    Explanations

    words related to changes, such as shifting, environmental, and transformations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes and their implications across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.82
     AUTH
    -0.76
    Quotes
    -0.75
    ç«
    -0.72
    alty
    -0.72
     Certification
    -0.72
    gerald
    -0.70
    atown
    -0.70
    é¾
    -0.70
    REL
    -0.69
    POSITIVE LOGITS
     effected
    0.96
    hyde
    0.89
     unpredict
    0.85
    gradient
    0.85
     wrought
    0.84
     phases
    0.83
     occurring
    0.83
     occur
    0.82
    iral
    0.78
    ilibrium
    0.78
    Act Density 0.075%

    No Known Activations