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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental methods and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rumania
    -0.72
     Efq
    -0.71
     Cæsar
    -0.70
     Shakspeare
    -0.69
     Sodom
    -0.68
    تقاوى
    -0.68
     Mahomet
    -0.67
    Portail
    -0.67
     AssemblyTitle
    -0.67
    GEBURTS
    -0.66
    POSITIVE LOGITS
     following
    0.55
     folgende
    0.53
     следующим
    0.50
     folgender
    0.50
     świad
    0.48
     []:
    0.47
     berikut
    0.45
     semp
    0.45
    ExtendWith
    0.45
     BoxFit
    0.44
    Act Density 0.728%

    No Known Activations