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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removal or deprivation of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "strip" and its variations in various contexts of removal or deprivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.95
    risome
    -0.77
    è¦ļéĨĴ
    -0.76
    anwhile
    -0.75
    NOR
    -0.71
    foreseen
    -0.65
    Interstitial
    -0.61
    midt
    -0.61
    arettes
    -0.61
    EEK
    -0.60
    POSITIVE LOGITS
     away
    0.89
     naked
    0.79
    utic
    0.76
    aways
    0.75
    lete
    0.72
     bare
    0.72
     redundant
    0.71
    leted
    0.70
     violet
    0.70
    ı
    0.70
    Act Density 0.070%

    No Known Activations