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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical or programming symbols and operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Merz
    -0.92
    ześnie
    -0.88
     Donato
    -0.85
     Coleridge
    -0.85
    </tfoot>
    -0.84
     resistors
    -0.82
    ValueStyle
    -0.82
     ._
    -0.81
    locke
    -0.81
     hydra
    -0.81
    POSITIVE LOGITS
    }{|
    1.16
    }{||
    0.93
    si
    0.68
    inSlope
    0.66
    alis
    0.60
     Ges
    0.59
    
    0.59
    mes
    0.58
    ne
    0.58
    vel
    0.58
    Act Density 0.002%

    No Known Activations