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

    Neuronpedia

    INDEX
    Explanations

    words related to technical specifications, particularly those involving hyphens

    oai_token-act-pair · gpt-3.5-turbo

    references to group names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -0.73
     partName
    -0.71
    enegger
    -0.67
    enting
    -0.65
    icut
    -0.64
    orders
    -0.62
    indal
    -0.61
    asks
    -0.59
    itzer
    -0.59
    aughter
    -0.58
    POSITIVE LOGITS
    pillar
    0.93
    ccording
    0.86
    Lago
    0.78
    RIC
    0.77
    MET
    0.73
    ENA
    0.72
    MT
    0.72
    Bs
    0.72
    ZE
    0.68
    ©¶æ¥µ
    0.68
    Act Density 0.053%

    No Known Activations