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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "despite" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascade
    -0.15
    .weixin
    -0.15
    ãĤ¹ãĤ³
    -0.15
    istrovstvÃŃ
    -0.15
    rum
    -0.14
    eteria
    -0.14
    ypy
    -0.14
    roperty
    -0.14
    dana
    -0.14
    ispens
    -0.13
    POSITIVE LOGITS
     being
    0.21
    u
    0.18
    oit
    0.15
    being
    0.15
    unnel
    0.14
     Being
    0.14
     Tüm
    0.14
     his
    0.14
    ooke
    0.14
    939
    0.14
    Act Density 0.018%

    No Known Activations