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

    Neuronpedia

    INDEX
    Explanations

    descriptions of events or projects at their early stages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vété
    -0.65
     getPost
    -0.55
     confé
    -0.51
    vstack
    -0.46
     congrès
    -0.44
     géant
    -0.44
     getPlayer
    -0.44
     Membre
    -0.44
     levier
    -0.44
    Madre
    -0.43
    POSITIVE LOGITS
     initial
    1.03
     Initial
    0.98
    initial
    0.97
    Initial
    0.96
     INITIAL
    0.93
    INITIAL
    0.83
     inicial
    0.81
    setInitial
    0.79
     iniciales
    0.78
    initialValue
    0.75
    Act Density 0.060%

    No Known Activations