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

    Neuronpedia

    INDEX
    Explanations

    phrases asking for information or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the phrase "what happened to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    voy
    -0.78
    é¾įåĸļ士
    -0.71
     topped
    -0.71
     Uses
    -0.69
    artisan
    -0.68
    à¼
    -0.68
    tips
    -0.65
    fork
    -0.65
    horn
    -0.64
    ãĤ¢ãĥ«
    -0.64
    POSITIVE LOGITS
    othy
    0.66
     trillions
    0.66
     Singer
    0.66
     ensure
    0.65
     transform
    0.65
     mutants
    0.63
     preserve
    0.63
     compensate
    0.63
    pless
    0.62
     safeguard
    0.61
    Act Density 0.061%

    No Known Activations