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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific locations or contextual settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orno
    -0.17
    achs
    -0.16
    ç¹
    -0.15
     blo
    -0.15
    172
    -0.15
    ¯ÃĤ
    -0.15
    rikes
    -0.15
    rike
    -0.14
    annie
    -0.14
    лоп
    -0.14
    POSITIVE LOGITS
     weekends
    0.29
     Weekend
    0.20
     weekend
    0.18
     source
    0.17
    GLOSS
    0.15
    affiliate
    0.15
     sourceMappingURL
    0.15
     grass
    0.15
    erdem
    0.14
    ائÙĩ
    0.14
    Act Density 0.073%

    No Known Activations