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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating potential outcomes or advantages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.77
     jupe
    -0.58
     impresora
    -0.55
     mijne
    -0.54
     táctil
    -0.52
     éditoriale
    -0.52
     électronique
    -0.52
     Suivez
    -0.51
     obé
    -0.51
     BorderSide
    -0.51
    POSITIVE LOGITS
     potential
    2.80
    potential
    2.61
    Potential
    2.53
     Potential
    2.53
     POTENTIAL
    2.33
     potencial
    2.17
     potensi
    1.91
     potentiel
    1.90
     poten
    1.88
     potenciales
    1.87
    Act Density 0.084%

    No Known Activations