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

    Neuronpedia

    INDEX
    Explanations

    sentences that express conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aro
    -0.16
    obel
    -0.15
    ople
    -0.15
    agos
    -0.15
    Ç
    -0.15
    aria
    -0.15
    oup
    -0.14
     mere
    -0.13
    inski
    -0.13
     Moor
    -0.13
    POSITIVE LOGITS
    kea
    0.15
    otive
    0.15
    æ²»
    0.14
    ystore
    0.14
    ãģ¾ãģŁ
    0.14
    ertoire
    0.14
    iaux
    0.14
     Åŀu
    0.14
    cü
    0.14
    637
    0.14
    Act Density 0.084%

    No Known Activations