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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of places or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ord
    -0.84
    ks
    -0.83
    key
    -0.80
    ibel
    -0.75
    keys
    -0.74
    ax
    -0.71
    ffen
    -0.71
    dn
    -0.70
    ads
    -0.70
    roman
    -0.70
    POSITIVE LOGITS
    FORM
    1.41
    ISH
    1.38
    IFIED
    1.33
    ER
    1.31
    LAND
    1.29
    MAN
    1.28
    FIELD
    1.28
    OUT
    1.28
    VILLE
    1.27
    ING
    1.26
    Act Density 0.089%

    No Known Activations