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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating presence or location, such as "There is" or "There's"

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol represented by "Ļ" within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jinn
    -0.65
     Mobil
    -0.63
     successes
    -0.63
     clones
    -0.61
     partnerships
    -0.61
     juggling
    -0.60
    è¦ļéĨĴ
    -0.60
     captives
    -0.60
     Kenyan
    -0.60
    anium
    -0.59
    POSITIVE LOGITS
    else
    0.95
    clear
    0.83
    uable
    0.81
    tu
    0.80
    abad
    0.79
    fter
    0.79
    outh
    0.78
    aternity
    0.78
    sure
    0.78
    Pg
    0.77
    Act Density 0.074%

    No Known Activations