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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adin
    -1.03
     Gors
    -0.88
    ãĥ´
    -0.83
    utm
    -0.81
    Els
    -0.81
    eatures
    -0.80
    poke
    -0.80
    =-=-
    -0.80
    angelo
    -0.77
    lvl
    -0.76
    POSITIVE LOGITS
     fame
    0.93
     frontman
    0.87
     syndrome
    0.82
     sequel
    0.79
     cosmetics
    0.76
     LLP
    0.75
     alum
    0.74
     heroine
    0.73
     staples
    0.73
     fiasco
    0.73
    Act Density 0.323%

    No Known Activations