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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or formal specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to non-qualifying conditions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yards
    -0.76
    ramids
    -0.75
    yip
    -0.72
    etts
    -0.69
    wings
    -0.69
     Rampage
    -0.69
     Yards
    -0.68
    stones
    -0.68
    wich
    -0.68
    sung
    -0.68
    POSITIVE LOGITS
     non
    3.09
    Non
    2.44
     Non
    2.41
    non
    2.34
     NON
    2.19
     nont
    1.92
     nons
    1.89
     nonex
    1.62
     nond
    1.61
     nonexistent
    1.24
    Act Density 0.034%

    No Known Activations