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

    Neuronpedia

    INDEX
    Explanations

    proper names starting with "Ar" followed by another letter

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Ar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sight
    -0.70
     functioning
    -0.64
     firsthand
    -0.62
    eners
    -0.62
     pathology
    -0.62
    ĨĴ
    -0.60
     birth
    -0.59
    ¬¼
    -0.57
     autop
    -0.57
     srfAttach
    -0.56
    POSITIVE LOGITS
    ithmetic
    1.20
    ranged
    1.19
    thritis
    1.18
    lene
    1.14
    rang
    1.11
    ansas
    1.10
    gue
    1.10
    rington
    1.10
    vind
    1.07
    agon
    1.06
    Act Density 0.016%

    No Known Activations