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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to monetary values or transactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     */}
    -0.71
    ilsen
    -0.69
     IES
    -0.67
     Ek
    -0.67
    paramref
    -0.66
     deb
    -0.66
     cic
    -0.66
    sein
    -0.65
    uksen
    -0.65
    みると
    -0.63
    POSITIVE LOGITS
     Foxx
    0.86
     Catto
    0.83
     pitié
    0.83
     
    0.81
     omnia
    0.81
    troppo
    0.80
     Shakspeare
    0.80
     sandero
    0.79
    ARGS
    0.79
     lettore
    0.79
    Act Density 0.070%

    No Known Activations