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

    Neuronpedia

    INDEX
    Explanations

    verbs related to consistency and stability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating stability or consistency over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raid
    -0.79
    dinand
    -0.74
    isson
    -0.71
    DragonMagazine
    -0.69
    panic
    -0.65
    ications
    -0.64
    displayText
    -0.63
    è¦ļéĨĴ
    -0.62
    warning
    -0.62
    LEY
    -0.61
    POSITIVE LOGITS
     unchanged
    1.44
     intact
    1.25
     afloat
    1.03
     unaffected
    1.02
     untouched
    1.00
     stagnant
    0.95
     stable
    0.93
     unch
    0.88
     steady
    0.87
     constant
    0.84
    Act Density 0.093%

    No Known Activations