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

    Neuronpedia

    INDEX
    Explanations

    expressions of doubt, negativity, and contrasting situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.81
    });*/
    -0.67
    SharedCtor
    -0.64
    SourceChecksum
    -0.63
    "]];
    -0.63
     ſtate
    -0.61
    MemoryWarning
    -0.59
    expandindo
    -0.58
     defaultstate
    -0.57
     Houſe
    -0.56
    POSITIVE LOGITS
     even
    1.47
    even
    1.29
     siquiera
    1.19
     Even
    1.13
    Even
    1.10
     EVEN
    1.09
     даже
    1.00
     même
    0.98
    EVEN
    0.98
     дори
    0.96
    Act Density 0.224%

    No Known Activations