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

    Neuronpedia

    INDEX
    Explanations

    the concept of splitting or dividing, often in the context of inputs and outputs in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Table
    -0.52
     non
    -0.52
     Eagle
    -0.52
     Pel
    -0.52
     Sta
    -0.52
     Gre
    -0.51
     F
    -0.51
     Vac
    -0.50
     Vel
    -0.50
     Fe
    -0.50
    POSITIVE LOGITS
     informée
    0.75
     jugador
    0.73
     joueur
    0.70
     INPUTS
    0.70
    Inputs
    0.69
     jugadores
    0.68
     players
    0.68
     joueurs
    0.66
     pájaro
    0.66
     spelers
    0.66
    Act Density 0.219%

    No Known Activations