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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating significance, impact, or consequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote implications or meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliate
    -0.69
    phrine
    -0.67
    oute
    -0.64
    Kings
    -0.64
    genre
    -0.63
    iban
    -0.63
    taboola
    -0.63
    ibble
    -0.63
    aughs
    -0.63
    @#&
    -0.62
    POSITIVE LOGITS
     goodbye
    1.02
     sacrificing
    0.72
     nothing
    0.68
    hift
    0.68
     fewer
    0.66
     something
    0.66
     shovel
    0.64
     spirited
    0.64
     risking
    0.62
     everything
    0.62
    Act Density 0.038%

    No Known Activations