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

    Neuronpedia

    INDEX
    Explanations

    general plural nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing the word "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cinderella
    -0.57
    Reader
    -0.56
    bal
    -0.55
    inth
    -0.55
     Sorceress
    -0.55
    etter
    -0.55
    flation
    -0.54
    Atl
    -0.54
     Maiden
    -0.54
    Es
    -0.54
    POSITIVE LOGITS
    ocating
    1.22
    uding
    1.16
    oys
    1.08
    ude
    1.07
    usions
    1.07
    ocated
    1.07
    udes
    1.06
    usion
    1.02
    igators
    0.99
     sorts
    0.96
    Act Density 0.058%

    No Known Activations