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

    Neuronpedia

    INDEX
    Explanations

    references to locations or entities, such as geographical areas or structures within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]`
    -0.86
    gnition
    -0.83
     Theſe
    -0.81
    </tfoot>
    -0.81
     pleaſure
    -0.80
     Vivid
    -0.80
    iffance
    -0.79
    hematical
    -0.79
    %\]
    -0.78
    eſt
    -0.78
    POSITIVE LOGITS
    ,
    0.60
    —
    0.53
    IntoConstraints
    0.46
     that
    0.43
    '
    0.42
    ...
    0.42
    --
    0.41
     where
    0.41
    …
    0.40
    E
    0.40
    Act Density 0.459%

    No Known Activations