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

    Neuronpedia

    INDEX
    Explanations

    phrases related to success, popularity, and cultural impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating success or popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.81
    essim
    -0.76
    izon
    -0.71
    erity
    -0.70
    jad
    -0.69
     Architects
    -0.68
    abama
    -0.67
    itton
    -0.67
    ĪĴ
    -0.67
    jri
    -0.65
    POSITIVE LOGITS
     popular
    1.30
     revered
    1.25
     beloved
    1.22
     acclaimed
    1.20
     bestselling
    1.17
     influential
    1.16
     renown
    1.15
     cult
    1.14
     recognizable
    1.13
     staple
    1.12
    Act Density 0.261%

    No Known Activations