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

    Neuronpedia

    INDEX
    Explanations

    passages that present compelling arguments or significant statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rei
    -0.15
     Silk
    -0.14
     Abb
    -0.14
     sketches
    -0.14
     Randall
    -0.13
    isor
    -0.13
     Highway
    -0.13
     shorter
    -0.13
    anco
    -0.13
     scenarios
    -0.13
    POSITIVE LOGITS
    odiac
    0.15
    :↵↵↵
    0.14
    ":↵
    0.14
     пÑĢибоÑĢ
    0.14
    :↵↵
    0.14
    .datasource
    0.14
    ]]:↵
    0.14
    para
    0.14
     quoted
    0.14
    REEN
    0.13
    Act Density 0.191%

    No Known Activations