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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or realization related to unfamiliarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.16
    ello
    -0.15
    etic
    -0.15
    esta
    -0.14
    ansas
    -0.14
    'class
    -0.14
     Bast
    -0.14
    idual
    -0.13
    rist
    -0.13
    ASA
    -0.13
    POSITIVE LOGITS
    ichern
    0.16
    usercontent
    0.16
    лÑĮÑĤ
    0.16
    zia
    0.14
    ahren
    0.14
    ropol
    0.14
    .Resume
    0.14
    erdem
    0.14
    roupon
    0.14
    é®
    0.14
    Act Density 0.131%

    No Known Activations