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

    Neuronpedia

    INDEX
    Explanations

    superlative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /current
    -0.15
    orny
    -0.15
    æ°ĹãģĮ
    -0.14
    arehouse
    -0.14
    amerate
    -0.14
     Dawson
    -0.14
    è¶
    -0.14
    οÏį
    -0.14
     happiest
    -0.13
    .digest
    -0.13
    POSITIVE LOGITS
     few
    0.20
     things
    0.16
    few
    0.16
     wen
    0.15
    Few
    0.14
    vore
    0.14
    OfClass
    0.14
     cle
    0.14
     liv
    0.14
    AGMA
    0.14
    Act Density 0.047%

    No Known Activations