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

    Neuronpedia

    INDEX
    Explanations

    phrases related to success and positive outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alli
    -0.16
     now
    -0.15
     acting
    -0.14
     uncompressed
    -0.14
    æĸ¹
    -0.14
    zos
    -0.14
    ÃŃc
    -0.13
    ednou
    -0.13
    bern
    -0.13
    ustos
    -0.13
    POSITIVE LOGITS
     success
    0.41
     successful
    0.37
    success
    0.34
     Success
    0.34
    æĪIJåĬŁ
    0.34
     successes
    0.34
     succès
    0.34
    Success
    0.33
     succes
    0.33
     succeed
    0.32
    Act Density 0.192%

    No Known Activations