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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statistical findings or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.28
    c
    -0.16
     Essentials
    -0.16
    noon
    -0.15
    RuntimeException
    -0.15
     particularly
    -0.14
    notated
    -0.14
     gql
    -0.14
    ories
    -0.14
    quoi
    -0.14
    POSITIVE LOGITS
    /of
    0.21
    ses
    0.20
    /or
    0.18
    /by
    0.18
    plevel
    0.17
    Ñģе
    0.17
    pired
    0.16
    pires
    0.16
    лÑĮ
    0.15
    ARRANT
    0.15
    Act Density 0.041%

    No Known Activations