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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duk
    -0.17
    ursed
    -0.17
    cheon
    -0.16
    yan
    -0.16
    ÑĮко
    -0.16
    ottage
    -0.16
    anches
    -0.15
    edicine
    -0.15
    elopment
    -0.14
    bish
    -0.14
    POSITIVE LOGITS
    èĮ¶
    0.17
    enti
    0.17
     rad
    0.14
    um
    0.14
    CAPE
    0.14
     mus
    0.14
     often
    0.14
     Wend
    0.14
     priv
    0.14
    çŁ
    0.14
    Act Density 0.026%

    No Known Activations