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

    Neuronpedia

    INDEX
    Explanations

    references to figures and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     navide
    -0.80
     cromado
    -0.79
     temporales
    -0.79
     démocr
    -0.78
     Económica
    -0.75
     européennes
    -0.75
     imidlertid
    -0.73
     groote
    -0.73
     vanske
    -0.73
     inferiores
    -0.73
    POSITIVE LOGITS
     defaultstate
    0.53
     wh
    0.51
    ⓧ
    0.49
     whe
    0.49
     fin
    0.49
     Fin
    0.49
     Wh
    0.49
     क
    0.49
     ane
    0.47
    OGND
    0.47
    Act Density 0.126%

    No Known Activations