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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a high degree or quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "some."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atten
    -0.70
    mie
    -0.65
    noon
    -0.64
    atars
    -0.63
    ossier
    -0.63
    ér
    -0.62
    jac
    -0.62
    acia
    -0.61
    eret
    -0.61
    eton
    -0.61
    POSITIVE LOGITS
     interesting
    1.11
     amazing
    1.11
     pretty
    1.09
     incredible
    1.08
     fantastic
    1.06
     fascinating
    1.06
     amazingly
    1.04
     incredibly
    1.04
     impressive
    1.04
     awfully
    1.04
    Act Density 0.119%

    No Known Activations